© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75598
    Prev
    Next
    INDEX
    Explanations

    Software/online management

    np_max-act-logits · 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
     "..\..\
    -0.42
    aimerais
    -0.40
    لاعب
    -0.39
     Phari
    -0.39
    ーマ
    -0.37
     météoro
    -0.37
    сомо
    -0.36
    MigrationBuilder
    -0.35
     Qur
    -0.34
     beginnetje
    -0.34
    POSITIVE LOGITS
    disposing
    0.71
     ब्रेकडाउन
    0.71
    enumi
    0.71
    RUnlock
    0.70
     Disk
    0.68
    enumii
    0.67
     Мексичка
    0.67
     NSError
    0.67
     république
    0.67
    httphttps
    0.66
    Activations Density 0.001%

    No Known Activations