© 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. 97671
    Prev
    Next
    INDEX
    Explanations

    league

    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
     COUNCIL
    -0.75
    Council
    -0.74
    ########.
    -0.73
     Council
    -0.70
    council
    -0.64
    saraba
    -0.59
    énario
    -0.57
    קישורים
    -0.56
    !")
    -0.56
    Lähteet
    -0.55
    POSITIVE LOGITS
     indépend
    0.56
     незавершена
    0.54
     Conventional
    0.52
    pragma
    0.50
    BeginContext
    0.50
     Either
    0.49
    cshtml
    0.49
     palk
    0.48
     вікі
    0.46
    Fuse
    0.46
    Activations Density 1.643%

    No Known Activations