© 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. 1-CLT-HP
    7. 15904
    Prev
    Next
    INDEX
    Explanations

    height

    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
     disambiguazione
    -0.64
    inghouse
    -0.53
     Tite
    -0.50
     Tada
    -0.49
     AspNetCore
    -0.49
    ISMS
    -0.48
     Drapeau
    -0.48
    <bos>
    -0.47
     وسط
    -0.47
     height
    -0.47
    POSITIVE LOGITS
     BoxFit
    0.79
    @[+][
    0.56
     valeurs
    0.55
     genomen
    0.54
    Попис
    0.53
    GHIJKLM
    0.52
    SPATH
    0.52
     cálculos
    0.52
     commerciales
    0.51
     pouvoirs
    0.50
    Activations Density 0.045%

    No Known Activations