© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 11490
    Prev
    Next
    INDEX
    Explanations

    questions and statements related to political candidates and elections

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    416
    +0.09
    0.3%
    81
    +0.08
    0.2%
    2008
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.09
    0.04
    416
    +0.08
    0.06
    1123
    +0.08
    0.06
    Negative Logits
     unwarran
    -1.06
     disagre
    -1.04
     indestru
    -0.98
     liberality
    -0.95
     tranf
    -0.93
     reft
    -0.91
     embodi
    -0.91
     sovere
    -0.91
     impractica
    -0.90
     unlaw
    -0.90
    POSITIVE LOGITS
     candidacy
    0.74
     candidates
    0.68
     kandid
    0.67
    awtextra
    0.67
     candidate
    0.66
     Demokrat
    0.66
     campaign
    0.63
     presidential
    0.61
     campaigns
    0.59
    candidate
    0.58
    Activations Density 0.578%

    No Known Activations