© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93917
    Prev
    Next
    INDEX
    Explanations

    fact

    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
     fact
    -0.80
     strain
    -0.50
     substrate
    -0.47
     FACT
    -0.46
     camera
    -0.45
     formula
    -0.45
     rat
    -0.45
    ]');
    -0.44
     cit
    -0.44
     mouse
    -0.44
    POSITIVE LOGITS
     незавершена
    0.83
    <bos>
    0.82
     autorytatywna
    0.82
    rungsseite
    0.81
    MigrationBuilder
    0.79
     الرياضيه
    0.77
     nahilalakip
    0.77
    setVerticalGroup
    0.76
    PerformLayout
    0.73
     للاسماء
    0.72
    Activations Density 0.081%

    No Known Activations