© 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. 77134
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    تقاوى
    -0.65
     estimés
    -0.59
     Савезне
    -0.59
    httphttps
    -0.57
    RUnlock
    -0.56
     CreateTagHelper
    -0.56
    styleUrls
    -0.55
    ControllerAdvice
    -0.55
    setVerticalGroup
    -0.55
    Identyfik
    -0.54
    POSITIVE LOGITS
     Clipper
    0.52
     Dit
    0.51
    PYX
    0.49
    ритори
    0.48
    seitige
    0.47
    VersionUID
    0.46
    itu
    0.44
     Blit
    0.43
    lets
    0.43
    orro
    0.42
    Activations Density 0.006%

    No Known Activations