© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97588
    Prev
    Next
    INDEX
    Explanations

    out

    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
    enumi
    -0.59
    >{"
    -0.49
    êle
    -0.47
    ışık
    -0.47
     off
    -0.46
    msen
    -0.46
     gawas
    -0.46
    {~
    -0.46
    ikt
    -0.46
    ized
    -0.44
    POSITIVE LOGITS
     BoxFit
    0.79
    GraphicsUnit
    0.63
    EndContext
    0.63
    setVerticalGroup
    0.60
    rungsseite
    0.59
     snippetHide
    0.58
     Euripides
    0.58
    VersionUID
    0.56
    IContainer
    0.55
     [],
    0.55
    Activations Density 0.014%

    No Known Activations