© 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. 77596
    Prev
    Next
    INDEX
    Explanations

    foreign words/code

    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
    iastes
    -0.54
    IsContent
    -0.50
    ngdoc
    -0.48
    Morfologia
    -0.47
     dig
    -0.45
     cli
    -0.45
    mappedBy
    -0.45
    rubin
    -0.44
     into
    -0.44
    Feeling
    -0.44
    POSITIVE LOGITS
    GraphicsUnit
    0.70
     للمعارف
    0.69
    fjspx
    0.63
    Lähteet
    0.54
    তথ্যসূত্র
    0.53
     PyLong
    0.53
    Дереккөздер
    0.53
    Viited
    0.52
    ContentAsync
    0.51
    Referencie
    0.51
    Activations Density 0.003%

    No Known Activations