© 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. 71605
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    providedIn
    -0.64
     createState
    -0.64
     warehouses
    -0.64
     nurseries
    -0.64
    stores
    -0.61
     protoimpl
    -0.60
    AutoScale
    -0.59
     compartments
    -0.58
    mergeFrom
    -0.58
     steder
    -0.58
    POSITIVE LOGITS
     terminal
    0.55
     HttpHeaders
    0.52
    geordneten
    0.49
    imageshack
    0.49
     computer
    0.49
     work
    0.48
     testing
    0.47
     building
    0.47
     Innovations
    0.46
    toggler
    0.46
    Activations Density 0.000%

    No Known Activations