© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1167
    Prev
    Next
    INDEX
    Explanations

    signs

    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
     Efq
    -1.12
     purpoſe
    -1.11
     plaques
    -1.06
     itſelf
    -1.06
     myſelf
    -1.05
     signs
    -1.04
    signs
    -1.04
     Jefus
    -1.03
     Reſ
    -1.03
     pleaſure
    -1.03
    POSITIVE LOGITS
     and
    0.82
     in
    0.78
     of
    0.77
     for
    0.75
     to
    0.72
    ,
    0.69
     (
    0.65
     as
    0.61
     or
    0.61
     are
    0.60
    Activations Density 0.301%

    No Known Activations