© 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. 12319
    Prev
    Next
    INDEX
    Explanations

    used

    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
     to
    -0.71
     ویکی‌پدیا
    -0.69
    Brainz
    -0.56
    లాలు
    -0.55
    MessageTagHelper
    -0.54
    binant
    -0.52
    contentLoaded
    -0.51
     protoimpl
    -0.50
    ագրություններ
    -0.50
    addPreferredGap
    -0.48
    POSITIVE LOGITS
    WebVitals
    0.50
     Ont
    0.48
     physical
    0.48
     MQ
    0.47
     Untold
    0.47
    RunWith
    0.47
     signUp
    0.46
    ائے
    0.46
     Schur
    0.46
     Physical
    0.46
    Activations Density 0.019%

    No Known Activations