© 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. 4-CLT-HP
    7. 3487
    Prev
    Next
    INDEX
    Explanations

    identifiers or codes

    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
     Waray
    -0.60
     hang
    -0.57
    lowy
    -0.57
    󠁢
    -0.53
     stanga
    -0.50
    ceros
    -0.50
    hang
    -0.46
     HANG
    -0.44
     wear
    -0.44
    hanging
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.78
    ftagPool
    0.73
    mergeFrom
    0.73
     pinulongan
    0.69
     باخ
    0.66
    aarrggbb
    0.63
    WindowConstants
    0.63
     autorytatywna
    0.60
    ьаж
    0.58
    IntoConstraints
    0.58
    Activations Density 0.030%

    No Known Activations