© 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. 5-CLT-HP
    7. 2202
    Prev
    Next
    INDEX
    Explanations

    defining terms

    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
    GenerationType
    -0.61
    PreferredItem
    -0.53
    White
    -0.51
     appreciating
    -0.51
    {}".
    -0.50
     مشين
    -0.50
     noting
    -0.50
     às
    -0.50
     by
    -0.49
    stepping
    -0.48
    POSITIVE LOGITS
    MigrationBuilder
    0.71
     esternos
    0.66
     ModelExpression
    0.61
    جغرافيا
    0.58
    uxxxx
    0.57
    DoubleQuotes
    0.55
     насељу
    0.53
    eqn
    0.52
     olsun
    0.51
    Koordinaten
    0.50
    Activations Density 0.008%

    No Known Activations