© 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. 0-CLT-HP
    7. 43961
    Prev
    Next
    INDEX
    Explanations

    spac

    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
     pos
    -0.62
    脚注の使い方
    -0.60
     tre
    -0.58
    isch
    -0.57
     scha
    -0.57
    UrlResolution
    -0.56
     auto
    -0.54
    complexContent
    -0.53
    cshtml
    -0.52
     om
    -0.51
    POSITIVE LOGITS
     Anſ
    0.83
     raiſ
    0.80
     myſelf
    0.77
     itſelf
    0.76
     uſ
    0.75
     Reſ
    0.73
     ་་
    0.70
     juſ
    0.69
     juſt
    0.69
     virš
    0.69
    Activations Density 0.080%

    No Known Activations