© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91188
    Prev
    Next
    INDEX
    Explanations

    hesitation

    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
     ModelExpression
    -0.87
     disambiguazione
    -0.74
     ProtoMessage
    -0.73
    TypedDataSet
    -0.69
     EconPapers
    -0.65
     TextInputType
    -0.65
    LookAnd
    -0.65
     समीक्षक
    -0.63
    tanleria
    -0.63
    AsUp
    -0.62
    POSITIVE LOGITS
     before
    0.66
     to
    0.63
    seamnă
    0.55
     duquel
    0.52
    before
    0.50
     teaching
    0.50
     zelve
    0.50
     ennen
    0.48
    teaching
    0.48
     ägg
    0.47
    Activations Density 0.001%

    No Known Activations