© 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. 5-CLT-HP
    4. 95155
    Prev
    Next
    INDEX
    Explanations

    while

    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
    migrationBuilder
    -0.79
     perfons
    -0.73
    MessageOf
    -0.73
     umane
    -0.68
    QMetaType
    -0.67
     umana
    -0.67
    MigrationBuilder
    -0.66
    demos
    -0.65
     needles
    -0.65
     a
    -0.65
    POSITIVE LOGITS
     trying
    0.42
     working
    0.42
     out
    0.41
     reorgan
    0.40
    флек
    0.39
    zeba
    0.38
     CanadaChoose
    0.38
     on
    0.37
    ViewFeatures
    0.37
    landı
    0.37
    Activations Density 0.004%

    No Known Activations