© 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. 71307
    Prev
    Next
    INDEX
    Explanations

    radio

    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
    PickerController
    -0.51
     Vac
    -0.47
    windig
    -0.44
     '\''
    -0.44
    EnableWeb
    -0.44
    ucket
    -0.44
    moid
    -0.43
    guerite
    -0.42
     Image
    -0.42
    findpost
    -0.41
    POSITIVE LOGITS
     AspNetCore
    0.86
    دانشنامهٔ
    0.71
    ThroughAttribute
    0.65
    يكب
    0.59
    utilisons
    0.59
     الاطلاع
    0.57
    ={({
    0.56
    OOTDTY
    0.55
    HON
    0.54
    béco
    0.54
    Activations Density 0.001%

    No Known Activations