© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42224
    Prev
    Next
    INDEX
    Explanations

    code comments

    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
     righteousness
    -1.48
     justicia
    -0.63
    richtet
    -0.60
     béné
    -0.56
    WRENCE
    -0.55
    verket
    -0.54
    jednoc
    -0.54
    letus
    -0.54
    Coment
    -0.52
     religieuses
    -0.50
    POSITIVE LOGITS
    URLException
    0.68
    contentLoaded
    0.66
     ModelExpression
    0.66
    matchCondition
    0.66
    Tikang
    0.65
    nestjs
    0.64
    ftagPool
    0.63
    AndEndTag
    0.63
    省市镇
    0.62
    niająca
    0.60
    Activations Density 0.218%

    No Known Activations