© 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. 43118
    Prev
    Next
    INDEX
    Explanations

    formal documents, code

    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
    nological
    -0.80
     himſelf
    -0.64
    ########.
    -0.63
    Geplaatst
    -0.63
    tagHelperRunner
    -0.61
     with
    -0.61
    abestanden
    -0.60
    UnusedPrivate
    -0.57
     itſelf
    -0.57
    CrossRef
    -0.56
    POSITIVE LOGITS
    <()>
    0.63
    extAlignment
    0.56
    databind
    0.52
    tative
    0.50
    LEncoder
    0.50
     insuffisamment
    0.49
    quim
    0.49
    thalam
    0.47
    quias
    0.46
     Italijani
    0.46
    Activations Density 0.532%

    No Known Activations