© 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. 1-CLT-HP
    7. 289
    Prev
    Next
    INDEX
    Explanations

    smell

    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
    kháu
    -0.71
    StoryboardSegue
    -0.70
    contentLoaded
    -0.69
    StructEnd
    -0.66
    featureID
    -0.65
    OrBuilder
    -0.57
    utenants
    -0.57
    EdgeInsets
    -0.56
    OGND
    -0.55
    MigrationBuilder
    -0.55
    POSITIVE LOGITS
    ropoda
    0.52
     useState
    0.51
    Einzelnachweise
    0.48
     altrimenti
    0.47
    adra
    0.47
    reciation
    0.47
    Luther
    0.46
    omoto
    0.46
     atentos
    0.46
    民主
    0.46
    Activations Density 0.007%

    No Known Activations