© 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. 1772
    Prev
    Next
    INDEX
    Explanations

    a

    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
    StoryboardSegue
    -0.75
    TypedDataSet
    -0.73
    principalColumn
    -0.71
    parsedMessage
    -0.70
    AnchorStyles
    -0.69
    SharedDtor
    -0.68
    yntaxException
    -0.66
    matchCondition
    -0.63
    Билгалдахарш
    -0.62
    GeoNames
    -0.62
    POSITIVE LOGITS
    .
    0.90
     native
    0.62
     nativo
    0.57
     länge
    0.55
     longtemps
    0.54
     portanto
    0.51
    .,
    0.51
     nativa
    0.50
     pauvres
    0.50
     obstante
    0.49
    Activations Density 0.026%

    No Known Activations