© 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. 97621
    Prev
    Next
    INDEX
    Explanations

    pherom

    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
     of
    -0.60
     pepper
    -0.60
     fore
    -0.54
     forest
    -0.53
     at
    -0.49
     Pepper
    -0.47
     on
    -0.47
     plans
    -0.46
    ٰ
    -0.45
     and
    -0.44
    POSITIVE LOGITS
    ing
    0.90
    ValueStyle
    0.76
     تضيفلها
    0.71
    ING
    0.71
     ويكيپيديا
    0.70
     مشين
    0.69
    Datuak
    0.69
    LookAnd
    0.68
     ویکی‌پدی
    0.68
    ings
    0.66
    Activations Density 0.191%

    No Known Activations