© 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. 91949
    Prev
    Next
    INDEX
    Explanations

    alls

    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
    ting
    -1.09
    ted
    -1.07
     Man
    -0.78
    all
    -0.76
     ting
    -0.70
    alls
    -0.68
    TING
    -0.62
    IsContent
    -0.56
    Man
    -0.51
    TED
    -0.50
    POSITIVE LOGITS
    rungsseite
    0.79
     cauſe
    0.78
     Theſe
    0.78
     Anſ
    0.77
     uſe
    0.73
     himſelf
    0.72
     whoſe
    0.72
     ſeveral
    0.72
     ſhould
    0.71
    حياته
    0.71
    Activations Density 0.068%

    No Known Activations