© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2588
    Prev
    Next
    INDEX
    Explanations

    instances of the word "can" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.31
    1.4%
    1124
    +0.11
    0.5%
    381
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1124
    +0.31
    0.06
    805
    +0.11
    0.05
    1974
    +0.11
    0.05
    Negative Logits
    <bos>
    -2.36
    <tfoot>
    -0.63
     /**
    -0.58
    /***
    -0.56
    //*/
    -0.54
    //};
    -0.53
    vierno
    -0.49
    })();
    -0.49
    mour
    -0.48
    ViewStyle
    -0.47
    POSITIVE LOGITS
     practition
    0.88
     accla
    0.83
     maneu
    0.81
     disreg
    0.80
     genshin
    0.79
     affor
    0.79
     reluct
    0.75
     uchiha
    0.75
     pymysql
    0.74
     Jambi
    0.72
    Activations Density 0.159%

    No Known Activations