© 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. 39945
    Prev
    Next
    INDEX
    Explanations

    recognize

    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
    rouvez
    -0.52
    CAPTION
    -0.50
    weder
    -0.44
    uttavia
    -0.43
    antaranya
    -0.41
    ciaż
    -0.41
     continuación
    -0.40
    ConstraintMaker
    -0.40
    WAUKEE
    -0.39
    ándonos
    -0.38
    POSITIVE LOGITS
    autoconfigure
    0.75
    GoogleApiClient
    0.73
    OGND
    0.66
    ::::::::
    0.66
    bewerken
    0.64
     Efq
    0.63
    يميديا
    0.63
    ніципалі
    0.63
     civilisation
    0.61
    {§
    0.60
    Activations Density 0.018%

    No Known Activations