© 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. 97751
    Prev
    Next
    INDEX
    Explanations

    Technical discussions

    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
     History
    -0.54
    u
    -0.47
    an
    -0.42
    History
    -0.42
    i
    -0.42
     Storia
    -0.40
    y
    -0.38
    f
    -0.37
    (
    -0.37
     abril
    -0.35
    POSITIVE LOGITS
    bootstrapcdn
    1.19
    تقاوى
    1.10
    ^(@)
    0.93
    encodeWith
    0.92
     estekak
    0.92
     Forumite
    0.90
    archiviato
    0.89
     оригіналу
    0.89
     Majefty
    0.88
    PerformLayout
    0.88
    Activations Density 1.495%

    No Known Activations