© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94444
    Prev
    Next
    INDEX
    Explanations

    decision

    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
    ///</
    -0.51
    hoeddwyd
    -0.50
    rungsseite
    -0.49
     råd
    -0.48
    pushFollow
    -0.48
    world
    -0.46
     vzd
    -0.46
    GEBURTSDATUM
    -0.45
    er
    -0.45
    aarrggbb
    -0.45
    POSITIVE LOGITS
     '\\;'
    0.63
     inoxydable
    0.57
     JAXBElement
    0.56
    spaceBetween
    0.56
     LIRE
    0.56
     armband
    0.56
     endregion
    0.55
    Facades
    0.54
     Архів
    0.54
    anmoins
    0.54
    Activations Density 0.045%

    No Known Activations