© 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. 72473
    Prev
    Next
    INDEX
    Explanations

    to

    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
    fony
    -0.57
    évaluateur
    -0.56
     Autorisations
    -0.55
    verifyException
    -0.54
     ويكيميديا
    -0.54
    Aholisi
    -0.53
    MigrationBuilder
    -0.52
    تقاوى
    -0.50
    GEBURTSDATUM
    -0.49
    氏
    -0.49
    POSITIVE LOGITS
     house
    0.69
     houses
    0.62
    ylvan
    0.53
    Tell
    0.53
     Tell
    0.52
    tells
    0.52
    Telling
    0.51
    curate
    0.51
    ReactDOM
    0.51
     censiti
    0.50
    Activations Density 0.001%

    No Known Activations