© 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. 92447
    Prev
    Next
    INDEX
    Explanations

    other

    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
    Portale
    -0.67
     JAXBElement
    -0.63
     <",
    -0.55
    WithIOException
    -0.53
    expandindo
    -0.53
    createCanvas
    -0.52
    Kanpo
    -0.52
    InjectAttribute
    -0.52
    بوابة
    -0.51
     متعلقه
    -0.50
    POSITIVE LOGITS
    so
    0.53
     so
    0.50
     vč
    0.50
    Eloquent
    0.49
     autorytatywna
    0.48
    ----</
    0.48
    pairment
    0.48
     pince
    0.47
     vermel
    0.47
    avari
    0.47
    Activations Density 0.002%

    No Known Activations