© 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. 73737
    Prev
    Next
    INDEX
    Explanations

    fine

    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
    Art
    -1.61
     Art
    -1.60
     Arts
    -1.59
    Arts
    -1.59
     Artist
    -1.48
     ARTS
    -1.48
     ART
    -1.46
    Artist
    -1.42
     arts
    -1.41
    arts
    -1.39
    POSITIVE LOGITS
     fine
    0.76
    fine
    0.71
     visual
    0.63
    Fine
    0.59
     Paglinawan
    0.59
     FINE
    0.55
    LookAnd
    0.54
    tagHelperRunner
    0.54
     Fine
    0.54
    ChildIndex
    0.54
    Activations Density 0.015%

    No Known Activations