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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14312
    Prev
    Next
    INDEX
    Explanations

    information related to political candidates, parties, 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
    599
    +0.09
    0.3%
    1120
    +0.09
    0.2%
    604
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.09
    0.03
    2045
    +0.09
    0.05
    1770
    +0.08
    0.04
    Negative Logits
    <bos>
    -0.73
     OMITTED
    -0.54
     directrice
    -0.51
    ByVersion
    -0.49
     Zwiebel
    -0.49
     CWE
    -0.48
     géographie
    -0.48
    Javadoc
    -0.47
     smtplib
    -0.47
    Geographie
    -0.47
    POSITIVE LOGITS
     unve
    0.96
     footh
    0.96
     gaily
    0.86
     Rine
    0.86
     Vaugh
    0.83
     fortn
    0.81
     McInt
    0.80
     McLaugh
    0.78
     Immig
    0.77
     maneu
    0.76
    Activations Density 0.442%

    No Known Activations