© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15964
    Prev
    Next
    INDEX
    Explanations

    botany

    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
    <bos>
    -0.66
    ReusableCell
    -0.59
     capuche
    -0.59
    sizeCache
    -0.58
    RuleContext
    -0.58
    WebVitals
    -0.56
    __*/
    -0.56
     '{@
    -0.55
     архивлан
    -0.54
     typelib
    -0.53
    POSITIVE LOGITS
     inversely
    0.55
     Secretariat
    0.52
    MERC
    0.52
     Dent
    0.48
     cordi
    0.45
     secretariat
    0.45
     Commen
    0.43
    Corresponding
    0.43
     newArray
    0.42
     الدولى
    0.42
    Activations Density 0.018%

    No Known Activations