© 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. 5-CLT-HP
    7. 91227
    Prev
    Next
    INDEX
    Explanations

    http

    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
     Padova
    -0.45
    ?',
    -0.45
    Aula
    -0.41
    FundMe
    -0.40
     Corse
    -0.40
    CloseHandle
    -0.39
    سام
    -0.39
     apoptotic
    -0.39
    mogat
    -0.39
    __',
    -0.39
    POSITIVE LOGITS
    migrationBuilder
    0.87
    sizeCache
    0.73
    contentLoaded
    0.72
     ProtoMessage
    0.71
    новниш
    0.68
    Portale
    0.68
    StoryboardSegue
    0.67
    ագրություններ
    0.66
    Tembelea
    0.66
    adpleegd
    0.65
    Activations Density 0.005%

    No Known Activations