© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73237
    Prev
    Next
    INDEX
    Explanations

    Code/technical language

    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
    StructEnd
    -0.82
    LookAnd
    -0.70
     mergeFrom
    -0.64
    kháu
    -0.63
    windowFixed
    -0.62
    PreferredItem
    -0.61
     nahilalakip
    -0.60
     stanovnika
    -0.60
     annuel
    -0.59
    webElementXpaths
    -0.59
    POSITIVE LOGITS
     useHistory
    0.50
    __":
    0.49
     pot
    0.48
     in
    0.46
    __':
    0.45
     useNavigate
    0.43
    providedIn
    0.43
    awtextra
    0.41
    __':
    0.41
     developed
    0.39
    Activations Density 0.000%

    No Known Activations