© 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. 95078
    Prev
    Next
    INDEX
    Explanations

    on

    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
    icity
    -0.43
     antaranya
    -0.38
    OrWhiteSpace
    -0.38
    外部リンク
    -0.38
    hubungan
    -0.37
    *************/
    -0.36
     referrerpolicy
    -0.35
     tehd
    -0.35
     创建时间
    -0.35
    sendStatus
    -0.34
    POSITIVE LOGITS
    MigrationBuilder
    0.85
    aarrggbb
    0.79
    ///</
    0.77
     jScrollPane
    0.77
    ConstraintMaker
    0.76
    localctx
    0.76
    protoimpl
    0.73
     Roskov
    0.73
    ]));
    0.72
     heapq
    0.72
    Activations Density 0.001%

    No Known Activations