© 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. 72204
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    MergeFrom
    -0.65
     Widodo
    -0.64
    دانشنامهٔ
    -0.56
     externi
    -0.54
     Mars
    -0.54
     Duma
    -0.54
     Marte
    -0.53
     Merdeka
    -0.53
     Directorate
    -0.52
     mars
    -0.52
    POSITIVE LOGITS
     समीक्षाओं
    0.52
    twimg
    0.49
    makeText
    0.48
    ľov
    0.47
    findpost
    0.47
    +#+
    0.47
    İstinadlar
    0.47
    ;#
    0.46
     nakalista
    0.45
     résist
    0.44
    Activations Density 0.000%

    No Known Activations