© 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. 20-CLT-HP
    7. 71882
    Prev
    Next
    INDEX
    Explanations

    Mixed content

    np_max-act-logits · 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
    Tikang
    -0.71
    PyExc
    -0.57
    AxisAlignment
    -0.57
     sī
    -0.54
    الإنجليزية
    -0.54
    ########.
    -0.52
    AsUp
    -0.52
     cherchés
    -0.51
    ℉
    -0.50
    addCriterion
    -0.49
    POSITIVE LOGITS
    BrowserModule
    0.59
     فريبيس
    0.50
     good
    0.50
     disambiguazione
    0.48
    tų
    0.48
     متحده
    0.47
    styleUrls
    0.47
     bonne
    0.45
     share
    0.44
     Umsatz
    0.44
    Activations Density 0.001%

    No Known Activations