© 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. 20-CLT-HP
    7. 74581
    Prev
    Next
    INDEX
    Explanations

    Code/Technical descriptions

    np_max-act-logits · 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
    出版年
    -0.73
    FieldBuilder
    -0.67
    Portail
    -0.66
    LookAnd
    -0.65
    lapsingToolbar
    -0.63
     sixth
    -0.60
     Sixth
    -0.59
    eriks
    -0.59
    mappedBy
    -0.57
    Życiorys
    -0.57
    POSITIVE LOGITS
    nene
    0.54
    stateProvider
    0.47
    rungsseite
    0.44
    BURGH
    0.43
     sini
    0.42
    7
    0.42
    DeleteCommand
    0.42
    SourceChecksum
    0.41
    gogo
    0.41
    SaveChangesAsync
    0.40
    Activations Density 0.000%

    No Known Activations