© 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. 689
    Prev
    Next
    INDEX
    Explanations

    uncommon vocabulary

    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
     FetchType
    -0.59
    ConstraintMaker
    -0.54
    dp
    -0.49
     Goddard
    -0.48
    kommen
    -0.48
     khuyến
    -0.47
    EditPart
    -0.47
     dents
    -0.47
     Tenggara
    -0.44
    utebol
    -0.44
    POSITIVE LOGITS
     متعلقه
    0.63
    GEBURTSDATUM
    0.58
     насељу
    0.57
    protoimpl
    0.55
    RenderAtEndOf
    0.54
    verwijspagina
    0.53
    AddHtmlAttribute
    0.52
    PerformLayout
    0.49
     Administrativna
    0.49
     Roskov
    0.49
    Activations Density 0.004%

    No Known Activations