© 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. 76388
    Prev
    Next
    INDEX
    Explanations

    legal/official contexts

    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
    NameInMap
    -0.80
    Personendaten
    -0.78
    RetentionPolicy
    -0.73
    Jeografia
    -0.72
     nahilalakip
    -0.71
    ItemLayout
    -0.69
     AssemblyCulture
    -0.68
    ValueStyle
    -0.66
    GeneratedCode
    -0.65
    CodeAttribute
    -0.65
    POSITIVE LOGITS
     Daw
    0.47
    metto
    0.44
    GetAsync
    0.44
     Pull
    0.43
     Col
    0.42
     sag
    0.42
    pi
    0.41
     pull
    0.41
     cal
    0.40
     Cal
    0.40
    Activations Density 0.003%

    No Known Activations