© 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. 77681
    Prev
    Next
    INDEX
    Explanations

    code/incomplete sentences

    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
    QSize
    -0.59
    rawDesc
    -0.59
    XMLSchema
    -0.58
    alised
    -0.56
     Signalez
    -0.54
     unknownFields
    -0.54
     authorised
    -0.54
     moat
    -0.53
    lapsingToolbar
    -0.53
    unknownFields
    -0.51
    POSITIVE LOGITS
     مشين
    0.63
    expandindo
    0.57
     дописавши
    0.54
    Tembelea
    0.54
     spot
    0.52
    HasForeignKey
    0.48
    himp
    0.47
    __*/
    0.46
     utafitiHapana
    0.46
     angef
    0.46
    Activations Density 0.000%

    No Known Activations