© 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. 20-CLT-HP
    7. 72442
    Prev
    Next
    INDEX
    Explanations

    Technical language snippets

    np_max-act-logits · 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
    AndEndTag
    -0.68
    SharedCtor
    -0.65
     CreateTagHelper
    -0.61
     onAnimation
    -0.59
    mapreduce
    -0.58
    ngdoc
    -0.57
    Poloha
    -0.56
     }{@
    -0.56
    jooq
    -0.55
    ArrowToggle
    -0.54
    POSITIVE LOGITS
    ais
    0.69
    aa
    0.65
    ae
    0.65
    ez
    0.57
    ova
    0.56
    ship
    0.55
    ade
    0.49
    stick
    0.48
    iums
    0.48
    aut
    0.48
    Activations Density 0.016%

    No Known Activations