© 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. 91009
    Prev
    Next
    INDEX
    Explanations

    CNS

    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
    ly
    -0.95
    ni
    -0.94
    nya
    -0.88
    len
    -0.80
    に
    -0.74
    nan
    -0.74
    r
    -0.73
    na
    -0.72
    nat
    -0.71
    م
    -0.71
    POSITIVE LOGITS
     raiſ
    0.97
     houſe
    0.97
     itſelf
    0.97
     Majefty
    0.95
     purpoſe
    0.93
     ſche
    0.90
     Reſ
    0.90
     Jefus
    0.90
     Efq
    0.90
     ་་
    0.90
    Activations Density 0.851%

    No Known Activations