© 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. 72656
    Prev
    Next
    INDEX
    Explanations

    say court

    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
     "..\..\..\
    -0.82
     архивлан
    -0.73
     CreateTagHelper
    -0.73
     ErrIntOverflow
    -0.73
    endphp
    -0.69
    tvguidetime
    -0.65
    PyExc
    -0.63
    CodeAttribute
    -0.62
    webElementXpaths
    -0.61
     "..\..\
    -0.59
    POSITIVE LOGITS
    clf
    0.45
     Maren
    0.45
    ctc
    0.43
    ätten
    0.42
    коменду
    0.42
     مواليد
    0.41
     mày
    0.40
    ct
    0.39
    ndata
    0.39
    AsUp
    0.39
    Activations Density 0.003%

    No Known Activations