© 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. 5-CLT-HP
    7. 91876
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · 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
    tvguidetime
    -0.70
    ⓧ
    -0.69
     quæ
    -0.58
     ComVisible
    -0.56
     habet
    -0.56
     typelib
    -0.55
    gister
    -0.55
     Económica
    -0.54
    CodeAttribute
    -0.53
     GenerationType
    -0.53
    POSITIVE LOGITS
     متعلقه
    0.60
     Cobb
    0.49
    FDRE
    0.47
     فريبيس
    0.46
     ceci
    0.45
     ""}
    0.45
     Kopp
    0.44
     Nul
    0.44
     cez
    0.43
    mení
    0.43
    Activations Density 0.001%

    No Known Activations