© 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. 91556
    Prev
    Next
    INDEX
    Explanations

    oder

    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
     GoogleFonts
    -0.61
    SourceChecksum
    -0.59
    #+#
    -0.57
    himovic
    -0.57
    potranspiration
    -0.57
    FontOfSize
    -0.56
    GEBURTS
    -0.56
    datagrid
    -0.55
     ffilmiau
    -0.54
     بيها
    -0.54
    POSITIVE LOGITS
    mis
    0.56
    alus
    0.50
    Pyx
    0.48
    getDrawable
    0.48
    mal
    0.47
    telijke
    0.47
    MIS
    0.46
    his
    0.45
    xlabel
    0.45
     pisos
    0.45
    Activations Density 0.000%

    No Known Activations