© 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. 72894
    Prev
    Next
    INDEX
    Explanations

    they

    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
     will
    -0.98
    will
    -0.81
    Will
    -0.75
    ll
    -0.73
     akan
    -0.68
     sẽ
    -0.68
    d
    -0.66
    ’
    -0.65
    \'
    -0.63
     Ll
    -0.63
    POSITIVE LOGITS
    liothèque
    0.60
    BeginContext
    0.54
    Personensuche
    0.52
     تضيفلها
    0.52
     is
    0.51
    Tikang
    0.47
    MigrationBuilder
    0.46
    photobucket
    0.46
     صوتيه
    0.45
     cherchés
    0.45
    Activations Density 0.008%

    No Known Activations