© 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. 5-CLT-HP
    7. 95151
    Prev
    Next
    INDEX
    Explanations

    mathematical questions

    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
    +#+#
    -0.63
    SharedDtor
    -0.61
    Escola
    -0.55
    tvguidetime
    -0.55
     InputDecoration
    -0.49
     aceptas
    -0.48
    enteric
    -0.48
    ULUM
    -0.48
    astie
    -0.48
     Dage
    -0.48
    POSITIVE LOGITS
    AndEndTag
    0.69
     onAnimation
    0.55
     loisirs
    0.51
    bouncycastle
    0.50
     riuscito
    0.49
     snippetHide
    0.49
    liothèque
    0.49
    AutoScaleMode
    0.47
    DeleteBehavior
    0.46
    UnusedPrivate
    0.46
    Activations Density 0.059%

    No Known Activations