© 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. 71543
    Prev
    Next
    INDEX
    Explanations

    self

    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
    tagHelperRunner
    -0.69
     Signalez
    -0.69
    бенок
    -0.65
    LookAnd
    -0.65
    protoimpl
    -0.65
     gynhyrchwyd
    -0.64
    Hozzáférés
    -0.64
    ExtendWith
    -0.63
    insics
    -0.63
     مشين
    -0.63
    POSITIVE LOGITS
     religieuse
    0.54
    reonine
    0.52
     étrangère
    0.50
     noix
    0.47
     respeito
    0.46
     sezione
    0.45
    WriteLiteral
    0.44
    ider
    0.43
     sû
    0.42
     oreilles
    0.40
    Activations Density 0.002%

    No Known Activations