© 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. 71716
    Prev
    Next
    INDEX
    Explanations

    Code parameters

    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
    hera
    -0.52
     tartalomajánló
    -0.50
    صیلات
    -0.49
     Ox
    -0.49
    ToRefresh
    -0.49
    Hozzáférés
    -0.49
     وتسجيلات
    -0.48
    ginous
    -0.47
    FV
    -0.47
    siah
    -0.47
    POSITIVE LOGITS
    tabular
    0.53
    ɵ
    0.52
    getParameters
    0.50
     Parameters
    0.49
     دى
    0.47
     kosme
    0.47
     InputDecoration
    0.47
     Weights
    0.47
    parameters
    0.46
    amqp
    0.45
    Activations Density 0.001%

    No Known Activations