© 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. 5-CLT-HP
    7. 92120
    Prev
    Next
    INDEX
    Explanations

    questions and/or menu

    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
    schild
    -0.53
    RUnlock
    -0.49
     an
    -0.45
     reca
    -0.44
    Iden
    -0.43
     gynhyrchwyd
    -0.43
    графія
    -0.43
    ynki
    -0.42
    visionnement
    -0.42
    蒙
    -0.41
    POSITIVE LOGITS
     estimés
    0.62
     Efq
    0.60
     kaarangay
    0.60
    TagHelpers
    0.60
     Himo
    0.58
     دیکھیے
    0.57
    thest
    0.56
    expandindo
    0.56
     greateſt
    0.54
     Signalez
    0.54
    Activations Density 0.000%

    No Known Activations