© 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. 20-CLT-HP
    7. 78167
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    Negative Logits
    SourceChecksum
    -0.66
    IsContent
    -0.65
    EndGlobalSection
    -0.64
    WebControls
    -0.59
    MessageOf
    -0.58
    ThroughAttribute
    -0.57
    messageInfo
    -0.57
    setVerticalGroup
    -0.57
     autorytatywna
    -0.56
    InjectAttribute
    -0.55
    POSITIVE LOGITS
     MonoBehaviour
    0.53
    acte
    0.52
    Hentet
    0.50
    zco
    0.50
     Мексичка
    0.48
    RectangleBorder
    0.46
     tamu
    0.45
    AVR
    0.45
     Acu
    0.45
     acte
    0.44
    Activations Density 0.000%

    No Known Activations