© 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. 97723
    Prev
    Next
    INDEX
    Explanations

    INC

    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
    oo
    -0.81
    ocrat
    -0.64
    таратура
    -0.60
    ly
    -0.59
    ocratic
    -0.59
    ness
    -0.57
     rev
    -0.57
    SequentialGroup
    -0.55
    äude
    -0.54
     للاسماء
    -0.54
    POSITIVE LOGITS
     CreateTagHelper
    0.74
     béné
    0.61
     gustaría
    0.56
    midler
    0.56
    djangoproject
    0.55
     néz
    0.54
     nahilalakip
    0.54
    GEBURTSDATUM
    0.52
     trajets
    0.52
     مشين
    0.52
    Activations Density 1.595%

    No Known Activations