© 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. 91147
    Prev
    Next
    INDEX
    Explanations

    words

    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
     Leland
    -0.59
     Karya
    -0.55
     estekak
    -0.54
     Walkover
    -0.54
    adé
    -0.50
    lasse
    -0.48
     Fillmore
    -0.48
    EndContext
    -0.48
    Awake
    -0.47
    Географиясе
    -0.46
    POSITIVE LOGITS
    +#+#
    0.59
    aarrggbb
    0.54
    :✨
    0.53
    UnknownFields
    0.52
    principalColumn
    0.50
    Demografie
    0.48
    perg
    0.48
    jsonwebtoken
    0.47
    IsMutable
    0.47
     للاسماء
    0.46
    Activations Density 0.000%

    No Known Activations