© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94782
    Prev
    Next
    INDEX
    Explanations

    Medical/Scientific contexts

    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
    XtraGrid
    -0.54
    AnchorStyles
    -0.52
    ỡng
    -0.50
     مشين
    -0.49
    SourceChecksum
    -0.48
     quæ
    -0.47
    AndEndTag
    -0.47
     poule
    -0.47
     picioare
    -0.47
     فريبيس
    -0.46
    POSITIVE LOGITS
     kasarigan
    0.65
    脚注の使い方
    0.63
     Réponses
    0.61
     المعيارى
    0.60
    etheless
    0.59
    GOTREF
    0.56
    KommentareTeilen
    0.54
    ,:);
    0.54
    andha
    0.53
    ledem
    0.53
    Activations Density 0.288%

    No Known Activations