© 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. 5-CLT-HP
    7. 93543
    Prev
    Next
    INDEX
    Explanations

    Years

    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
    AddTagHelper
    -0.73
    новништво
    -0.60
     HttpNotFound
    -0.53
    letic
    -0.53
     كومونز
    -0.51
     useDispatch
    -0.50
     NSCoder
    -0.49
    (!__
    -0.48
    RectangleBorder
    -0.48
     kaynağından
    -0.48
    POSITIVE LOGITS
    }\]
    0.66
    "];
    0.64
    TagMode
    0.60
    </strong>
    0.59
    "];
    0.57
    wieś
    0.56
     gebracht
    0.56
     gewor
    0.55
     afstand
    0.53
    </h4>
    0.52
    Activations Density 0.003%

    No Known Activations