© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1624
    Prev
    Next
    INDEX
    Explanations

    of

    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
    déric
    -0.57
     ơn
    -0.54
    pired
    -0.52
    דרך
    -0.52
     teken
    -0.52
    orin
    -0.50
    rolid
    -0.50
     Cowan
    -0.50
    צלחה
    -0.50
    rophoresis
    -0.49
    POSITIVE LOGITS
    ⓧ
    0.74
    IsContent
    0.69
    providedIn
    0.63
    canestro
    0.59
     GenerationType
    0.58
    WebElementEntity
    0.58
    GeneratedMessage
    0.57
    Décès
    0.57
     виправивши
    0.57
    AnimationFrame
    0.55
    Activations Density 0.242%

    No Known Activations