© 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. 91145
    Prev
    Next
    INDEX
    Explanations

    discusses

    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
     Мексичка
    -1.11
    rrggbb
    -0.99
     discusses
    -0.81
    WithIOException
    -0.81
    Portail
    -0.79
     itſelf
    -0.77
     Houſe
    -0.77
     snippetHide
    -0.76
    CloseOperation
    -0.74
     ་་
    -0.73
    POSITIVE LOGITS
     in
    0.57
     take
    0.54
     change
    0.53
     how
    0.52
    freiheit
    0.52
     tag
    0.51
     the
    0.51
     with
    0.50
     on
    0.50
     Union
    0.49
    Activations Density 0.679%

    No Known Activations