© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45177
    Prev
    Next
    INDEX
    Explanations

    as

    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
     as
    -0.98
     in
    -0.68
     (
    -0.65
     for
    -0.65
     from
    -0.61
     to
    -0.57
    (
    -0.57
     on
    -0.57
     into
    -0.54
     along
    -0.54
    POSITIVE LOGITS
    MigrationBuilder
    1.13
     itſelf
    1.10
    NameInMap
    1.08
    ArgsConstructor
    1.06
    ^(@)
    1.05
    tanleria
    1.03
    WithIOException
    1.01
     poffible
    0.97
    TintMode
    0.96
     nahilalakip
    0.96
    Activations Density 0.093%

    No Known Activations