© 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. 71987
    Prev
    Next
    INDEX
    Explanations

    Mixed proper nouns and terms

    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
    ="@+
    -0.60
    IBar
    -0.58
    HtmlAttribute
    -0.56
    AxisAlignment
    -0.53
    :✨
    -0.50
    Naissance
    -0.50
    Cyfeiriadau
    -0.49
     sympy
    -0.49
     BoxDecoration
    -0.49
    shaft
    -0.49
    POSITIVE LOGITS
     Enter
    0.64
     Braid
    0.62
    providedIn
    0.60
     Ex
    0.58
    Enter
    0.55
     Pilgrim
    0.55
    Ex
    0.54
    zole
    0.52
    WebVitals
    0.50
    ็จ
    0.49
    Activations Density 0.000%

    No Known Activations