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

    Neuronpedia

    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. 4399
    Prev
    Next
    INDEX
    Explanations

    phrases related to political disputes and military activity

    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
    690
    +0.10
    0.3%
    1510
    +0.09
    0.3%
    1842
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1510
    +0.10
    0.04
    536
    +0.09
    0.03
    1265
    +0.08
    0.03
    Negative Logits
     quoique
    -1.76
     emphat
    -1.67
     increa
    -1.66
     sappi
    -1.65
     volunte
    -1.65
     Augu
    -1.63
     excru
    -1.63
     fta
    -1.61
     disagre
    -1.59
     indestru
    -1.59
    POSITIVE LOGITS
     etc
    0.98
    etc
    0.89
     그리고
    0.85
    …
    0.81
     but
    0.80
     ...
    0.80
     and
    0.80
     even
    0.79
     …
    0.79
    ...
    0.77
    Activations Density 0.215%

    No Known Activations