© 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. 97756
    Prev
    Next
    INDEX
    Explanations

    technical/scientific contexts

    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
    ing
    -0.82
    ING
    -0.66
    s
    -0.65
     
    -0.63
    ی
    -0.59
    a
    -0.56
    o
    -0.56
     respectivas
    -0.53
     O
    -0.52
     o
    -0.52
    POSITIVE LOGITS
     itſelf
    1.63
     myſelf
    1.61
     Efq
    1.52
     Monfieur
    1.50
     himſelf
    1.42
     ་་
    1.42
     Theſe
    1.42
     Jefus
    1.41
     ―――――
    1.41
     raiſ
    1.38
    Activations Density 0.428%

    No Known Activations