© 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. 998
    Prev
    Next
    INDEX
    Explanations

    single entity

    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
     Audiodateien
    -0.57
    __*/
    -0.56
     domestiques
    -0.55
     costumes
    -0.53
     components
    -0.53
     facilité
    -0.53
     ingredients
    -0.52
     members
    -0.50
    ArgsConstructor
    -0.49
    :✨
    -0.49
    POSITIVE LOGITS
     person
    0.70
    setof
    0.60
     perſon
    0.57
     vérit
    0.56
     prochaines
    0.56
     entity
    0.53
    NavController
    0.53
     utterance
    0.53
    essero
    0.52
     HasFactory
    0.52
    Activations Density 0.041%

    No Known Activations