© 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. 90894
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    Negative Logits
    AddTagHelper
    -0.66
    tvguidetime
    -0.63
    matchCondition
    -0.59
    ArgsConstructor
    -0.57
    LayoutStyle
    -0.53
     }}$}
    -0.53
     мәкал
    -0.52
    intios
    -0.51
     لها
    -0.50
     AssemblyCompany
    -0.50
    POSITIVE LOGITS
    -
    0.66
     autorytatywna
    0.60
    enumi
    0.60
    .
    0.56
    Composable
    0.56
    PropertyChanging
    0.55
     esimer
    0.55
     insuffisamment
    0.54
    subpackage
    0.53
     arvio
    0.53
    Activations Density 0.001%

    No Known Activations