© 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. 5-CLT-HP
    7. 94970
    Prev
    Next
    INDEX
    Explanations

    children and ages

    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
    otto
    -0.52
     correctes
    -0.50
    wicket
    -0.50
     Exactos
    -0.50
    }{*}{
    -0.50
     ivelany
    -0.49
    لسلة
    -0.49
     Simple
    -0.48
    Välislingid
    -0.48
    poise
    -0.47
    POSITIVE LOGITS
     LUMP
    0.57
    期刊论文
    0.49
    QtWidgets
    0.49
     ſche
    0.48
     ſmall
    0.47
    errHandler
    0.47
     Majefty
    0.47
     ſtate
    0.46
    Grüsse
    0.46
     Forumite
    0.46
    Activations Density 0.004%

    No Known Activations