© 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. 5-CLT-HP
    7. 3789
    Prev
    Next
    INDEX
    Explanations

    Random words/short strings

    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
     INDIAN
    -0.45
    cheibe
    -0.43
    npmjs
    -0.43
    gelöst
    -0.43
     Indian
    -0.42
    Indian
    -0.42
     nướng
    -0.41
    WEBPACK
    -0.41
    AppMethodBeat
    -0.41
    meability
    -0.40
    POSITIVE LOGITS
    TintMode
    0.62
    ніципалі
    0.55
    onnais
    0.54
     getItemId
    0.54
    ArgsConstructor
    0.54
    AddTagHelper
    0.52
     Meksiku
    0.52
    __':
    0.52
    onOptions
    0.52
     kohta
    0.51
    Activations Density 0.001%

    No Known Activations