© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4970
    Prev
    Next
    INDEX
    Explanations

    negations or expressions of inability and restrictions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.33
    1.7%
    1124
    +0.13
    0.7%
    878
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    878
    +0.33
    0.06
    1124
    +0.13
    0.05
    1097
    +0.11
    0.05
    Negative Logits
    <bos>
    -2.04
    /***
    -0.87
     intersper
    -0.70
     /**
    -0.64
     endow
    -0.64
    ///**
    -0.64
    habited
    -0.59
    timately
    -0.56
     harmonize
    -0.56
     disarm
    -0.53
    POSITIVE LOGITS
    ikkert
    0.74
    iligt
    0.73
     affez
    0.72
     sorella
    0.71
     vicina
    0.69
     venuto
    0.68
     pollut
    0.65
     fatte
    0.65
    :"-
    0.65
     friable
    0.64
    Activations Density 0.099%

    No Known Activations