© 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. 43124
    Prev
    Next
    INDEX
    Explanations

    Fraser

    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
     atrium
    -0.75
    TypedDataSet
    -0.70
     labs
    -0.68
    Hochspringen
    -0.65
    Lähteet
    -0.65
     AttributeSet
    -0.62
     Crawl
    -0.61
    __*/
    -0.60
     crawl
    -0.60
    lux
    -0.59
    POSITIVE LOGITS
    alnız
    0.57
     kuin
    0.47
    bac
    0.46
     conviene
    0.46
    dafx
    0.45
     uncin
    0.45
     pedras
    0.45
    yorsunuz
    0.44
    træ
    0.44
    exec
    0.43
    Activations Density 0.076%

    No Known Activations