© 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. 1072
    Prev
    Next
    INDEX
    Explanations

    valued

    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
     El
    -1.13
     valued
    -0.93
     modified
    -0.87
    El
    -0.82
     gal
    -0.79
     trials
    -0.77
    modified
    -0.72
     E
    -0.70
     Gal
    -0.70
     a
    -0.69
    POSITIVE LOGITS
     Reſ
    1.14
     Diſ
    1.13
     Efq
    1.12
     itſelf
    1.11
     Houſe
    1.10
     Monfieur
    1.08
    ſelves
    1.05
     houſe
    1.05
     becauſe
    1.05
     Majefty
    1.05
    Activations Density 0.206%

    No Known Activations