© 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. 90979
    Prev
    Next
    INDEX
    Explanations

    appeal

    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
     بيها
    -0.88
     oprot
    -0.70
    มาะ
    -0.66
     propOrder
    -0.64
    piac
    -0.59
    uxxxx
    -0.58
     Приступљено
    -0.57
    ########.
    -0.57
    esModule
    -0.57
     HasFactory
    -0.56
    POSITIVE LOGITS
    Brainz
    0.49
    SOUNDBITE
    0.47
     AssemblyCulture
    0.47
    서
    0.47
    SequentialGroup
    0.46
    troppo
    0.45
     launch
    0.45
    LabelTagHelper
    0.42
     volume
    0.41
    launch
    0.41
    Activations Density 0.010%

    No Known Activations