© 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. 20-CLT-HP
    7. 74491
    Prev
    Next
    INDEX
    Explanations

    Legal/Patent text

    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
    expandindo
    -0.53
    adă
    -0.47
    seitige
    -0.47
    MigrationBuilder
    -0.46
    StreetMap
    -0.46
    seitigen
    -0.43
    Acc
    -0.43
    Ga
    -0.42
    Gov
    -0.41
    佗
    -0.41
    POSITIVE LOGITS
     myſelf
    0.79
     themſelves
    0.77
     himſelf
    0.77
    ReusableCell
    0.73
     itſelf
    0.72
     Monfieur
    0.71
     ſeveral
    0.69
     greateſt
    0.64
     purpoſe
    0.63
     Partagez
    0.63
    Activations Density 0.010%

    No Known Activations