© 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. Gemma-2-2B
    5. 4-CLT-HP
    7. 2068
    Prev
    Next
    INDEX
    Explanations

    overall

    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
    antMatchers
    -0.57
     is
    -0.56
     was
    -0.56
    WritableDatabase
    -0.55
     as
    -0.53
     would
    -0.49
     differs
    -0.49
    AutoField
    -0.49
     of
    -0.48
     continues
    -0.48
    POSITIVE LOGITS
    SharedCtor
    0.73
    <bos>
    0.68
     prognosis
    0.65
     impact
    0.65
     consensus
    0.65
     number
    0.62
     message
    0.59
     effect
    0.58
     verdict
    0.58
     jLabel
    0.58
    Activations Density 0.002%

    No Known Activations