© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75471
    Prev
    Next
    INDEX
    Explanations

    of

    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
    SafeMath
    -0.48
     ब्रेकडाउन
    -0.47
    Activités
    -0.45
     Block
    -0.44
     saites
    -0.44
    ::_('
    -0.43
     khỏe
    -0.43
    bootstrapcdn
    -0.43
    TableHead
    -0.43
    tearDown
    -0.42
    POSITIVE LOGITS
    ніципалі
    0.57
    __*/
    0.56
    iastes
    0.56
    Diwedd
    0.55
    @[+][
    0.53
     talaga
    0.53
     INTERESAR
    0.53
    Бахар
    0.52
    RectangleBorder
    0.52
    ürtel
    0.52
    Activations Density 0.000%

    No Known Activations