© 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. 4-CLT-HP
    7. 483
    Prev
    Next
    INDEX
    Explanations

    Mixed, random, informal language

    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
    AndEndTag
    -0.73
    DockStyle
    -0.65
    SharedDtor
    -0.59
    hülle
    -0.57
    olsa
    -0.55
    RetentionPolicy
    -0.55
     cares
    -0.54
     Moines
    -0.54
     Florence
    -0.53
     Fears
    -0.52
    POSITIVE LOGITS
     समीक्षाओं
    0.65
     esterni
    0.53
    oa̍t
    0.49
    WebElementEntity
    0.47
     ISNI
    0.47
     véri
    0.43
     énergé
    0.43
     regioni
    0.43
    grà
    0.43
    damento
    0.42
    Activations Density 0.002%

    No Known Activations