© 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. 72450
    Prev
    Next
    INDEX
    Explanations

    programming / code

    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
    خط
    -0.50
    AddHtmlAttribute
    -0.48
     tráng
    -0.45
     nabí
    -0.45
     simplex
    -0.44
     Listed
    -0.44
     adal
    -0.43
     sixth
    -0.42
    trage
    -0.42
    тиза
    -0.42
    POSITIVE LOGITS
     cherchés
    0.66
    Референце
    0.64
    Revenir
    0.62
    SharedDtor
    0.61
     betweenstory
    0.60
    hofen
    0.58
     Winthrop
    0.54
     MainAxisSize
    0.54
     CiNii
    0.53
    featureID
    0.52
    Activations Density 0.002%

    No Known Activations