© 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. 0-CLT-HP
    7. 42258
    Prev
    Next
    INDEX
    Explanations

    code, configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RetentionPolicy
    -0.63
    agg
    -0.56
     setw
    -0.53
     Spisak
    -0.53
     gering
    -0.52
     Drugs
    -0.51
    igl
    -0.51
    ental
    -0.50
    pédie
    -0.50
    JOS
    -0.50
    POSITIVE LOGITS
    bewerken
    0.75
     autorytatywna
    0.67
     ExecuteAsync
    0.67
    LookAnd
    0.65
     initComponents
    0.63
     समीक्षाओं
    0.60
     виправивши
    0.59
    +#+
    0.57
     useDispatch
    0.57
     simplifié
    0.56
    Activations Density 0.134%

    No Known Activations