© 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. 1-CLT-HP
    7. 45806
    Prev
    Next
    INDEX
    Explanations

    Returning and behind

    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
    íncipe
    -0.53
    erdings
    -0.52
    pagna
    -0.50
     opérateur
    -0.48
    گشت
    -0.48
    tská
    -0.48
    tificates
    -0.47
    клопе
    -0.47
    innerText
    -0.47
    merce
    -0.47
    POSITIVE LOGITS
     Roskov
    0.70
    LookAnd
    0.67
    awtextra
    0.60
     متعلقه
    0.60
    DoubleQuotes
    0.59
    الحياه
    0.58
    +#+#
    0.58
    SequentialGroup
    0.56
    PrototypeOf
    0.56
    ähig
    0.56
    Activations Density 0.009%

    No Known Activations