© 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. 71407
    Prev
    Next
    INDEX
    Explanations

    Eugen

    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
    -0.54
     Walkover
    -0.48
    orsese
    -0.47
     WQS
    -0.46
    ViewImports
    -0.46
    NameInMap
    -0.45
    onOptions
    -0.45
    HAUS
    -0.45
     hennes
    -0.44
    kloped
    -0.44
    POSITIVE LOGITS
    itta
    0.72
    ina
    0.71
    inne
    0.69
    etta
    0.69
    essa
    0.67
    ína
    0.67
    ita
    0.66
    Rüyada
    0.64
    inna
    0.64
    na
    0.62
    Activations Density 0.004%

    No Known Activations