© 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. 20-CLT-HP
    7. 73458
    Prev
    Next
    INDEX
    Explanations

    net

    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
    ModelAdmin
    -0.65
    DataAnnotations
    -0.62
    addContainerGap
    -0.61
    grà
    -0.60
    antMatchers
    -0.59
     يتيمه
    -0.59
     дописавши
    -0.58
     AssemblyCulture
    -0.57
     Gilman
    -0.57
    Роди
    -0.56
    POSITIVE LOGITS
     发表于
    0.49
    enum
    0.47
    tles
    0.45
    UPO
    0.43
     APPELLATE
    0.42
    Oneof
    0.41
     otomatig
    0.41
    tle
    0.41
    ;->
    0.41
    เป
    0.40
    Activations Density 0.004%

    No Known Activations