© 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. 94307
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous website text snippets

    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
    ppchen
    -0.50
     ögon
    -0.48
     deber
    -0.47
     Kapital
    -0.46
    лики
    -0.45
    politan
    -0.45
    ARE
    -0.45
    umptive
    -0.45
     sekali
    -0.45
     afec
    -0.44
    POSITIVE LOGITS
    RegressionTest
    0.69
    jface
    0.64
     Roskov
    0.63
    Hochspringen
    0.63
    Jereo
    0.62
    LookAnd
    0.61
     OFDb
    0.60
    addCriterion
    0.59
    angliski
    0.58
    endregion
    0.58
    Activations Density 1.743%

    No Known Activations