© 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. 4-CLT-HP
    7. 708
    Prev
    Next
    INDEX
    Explanations

    all

    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
    endforeach
    -0.73
     ISNI
    -0.66
    ])):
    -0.65
    XmlAccessType
    -0.65
    contentLoaded
    -0.64
    öffentlichungen
    -0.63
     MenuView
    -0.62
     propOrder
    -0.60
    parsedMessage
    -0.60
     JpaRepository
    -0.60
    POSITIVE LOGITS
    WriteTagHelper
    0.49
    itaire
    0.48
     blank
    0.46
     ویکی‌پدیای
    0.46
    in
    0.46
     Taus
    0.45
    ливо
    0.45
     to
    0.42
    blank
    0.41
    jenigen
    0.41
    Activations Density 0.005%

    No Known Activations