Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11001
    Prev
    Next
    INDEX
    Explanations

    appropriations

    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
    QMetaType
    -0.89
    ReusableCell
    -0.88
     EconPapers
    -0.79
    didSet
    -0.75
    enterOuterAlt
    -0.73
     TestBed
    -0.73
     telefónica
    -0.73
    WebElementEntity
    -0.71
    NameInMap
    -0.69
     vägen
    -0.68
    POSITIVE LOGITS
    geth
    0.52
    bree
    0.42
    n
    0.41
     cer
    0.41
     tribut
    0.41
    cara
    0.40
     Biro
    0.39
    ommen
    0.39
     failing
    0.38
    no
    0.38
    Activations Density 0.016%

    No Known Activations