© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1022
    Prev
    Next
    INDEX
    Explanations

    uses of the word "is" or "'s" followed by words indicating explanations or subjective impressions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -1.00
     autorytatywna
    -0.91
     ModelExpression
    -0.85
    الدراسه
    -0.74
    uxxxx
    -0.73
    PerformLayout
    -0.67
    EndProject
    -0.67
    featureID
    -0.66
     ligiloj
    -0.66
     ostavi
    -0.66
    POSITIVE LOGITS
     how
    0.83
     where
    0.80
     what
    0.72
     the
    0.63
     our
    0.61
     their
    0.61
     a
    0.57
    where
    0.57
     true
    0.53
     noqa
    0.53
    Activations Density 0.273%

    No Known Activations