© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 450
    Prev
    Next
    INDEX
    Explanations

    programming/code

    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
    WebVitals
    -0.52
    וויק
    -0.45
     vientre
    -0.43
     hombros
    -0.41
     webbplats
    -0.39
     porcelaine
    -0.38
    Gön
    -0.38
    べき
    -0.38
     foncé
    -0.38
     manchas
    -0.36
    POSITIVE LOGITS
     purpoſe
    0.69
     protoimpl
    0.69
    SharedDtor
    0.69
     typelib
    0.68
     itſelf
    0.68
    MigrationBuilder
    0.64
     ſeveral
    0.64
     occaf
    0.64
     myſelf
    0.64
     Efq
    0.63
    Activations Density 0.117%

    No Known Activations