© 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. 77361
    Prev
    Next
    INDEX
    Explanations

    Non-English 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
    MigrationBuilder
    -0.84
     AttributeSet
    -0.83
     mxArray
    -0.80
    bootstrapcdn
    -0.73
    GeneratedValue
    -0.70
    banyak
    -0.66
     թվական
    -0.64
    SharedCtor
    -0.63
    ตร์
    -0.63
     PLWABN
    -0.63
    POSITIVE LOGITS
     مشين
    0.57
    肇
    0.43
     blessed
    0.43
    rik
    0.42
     gese
    0.41
     ge
    0.41
    XmlAccessType
    0.40
     se
    0.39
    geo
    0.38
     endowed
    0.38
    Activations Density 0.000%

    No Known Activations