© 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. 5-CLT-HP
    7. 5891
    Prev
    Next
    INDEX
    Explanations

    product

    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
     several
    -0.69
     various
    -0.63
    UrlResolution
    -0.63
    __':
    -0.62
     resourceCulture
    -0.58
    AnchorStyles
    -0.57
     mehrfach
    -0.57
    :]:
    -0.57
     Lightboxes
    -0.57
     Several
    -0.56
    POSITIVE LOGITS
     vš
    0.48
    łucha
    0.46
     ویکی‌پدی
    0.45
    LogFactory
    0.45
     castles
    0.44
     nominations
    0.44
     murders
    0.44
     empires
    0.44
     continents
    0.44
     chinoise
    0.44
    Activations Density 0.016%

    No Known Activations