© 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. 348
    Prev
    Next
    INDEX
    Explanations

    pancakes and baked goods

    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
    SBATCH
    -0.55
    utes
    -0.53
    rini
    -0.52
     officielles
    -0.52
     ब्रेकडाउन
    -0.51
    Hauptartikel
    -0.51
    far
    -0.49
    bots
    -0.49
    alts
    -0.49
    Tembelea
    -0.48
    POSITIVE LOGITS
    intios
    0.59
    ########.
    0.59
    ConstraintMaker
    0.57
    DebuggerNonUser
    0.56
     समीक्षक
    0.56
    脚注の使い方
    0.56
    ScopeManager
    0.55
     WMA
    0.54
    UnusedPrivate
    0.54
     Commande
    0.52
    Activations Density 0.014%

    No Known Activations