© 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. 4-CLT-HP
    7. 3503
    Prev
    Next
    INDEX
    Explanations

    to

    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
    NUMX
    -0.57
     disambiguazione
    -0.55
     spill
    -0.54
    CHLOR
    -0.54
     ErrorMessage
    -0.54
    pyrene
    -0.54
    perturb
    -0.53
     XNUMX
    -0.53
    ORIES
    -0.52
    GeneratedValue
    -0.52
    POSITIVE LOGITS
     виправивши
    0.55
    migrationBuilder
    0.52
    FieldBuilder
    0.50
    WriteLiteral
    0.49
     Berührung
    0.47
     InputDecoration
    0.47
    θέ
    0.47
    eran
    0.45
     povo
    0.44
    Diweddarwch
    0.44
    Activations Density 0.002%

    No Known Activations