© 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. 1-CLT-HP
    7. 9459
    Prev
    Next
    INDEX
    Explanations

    Virginia

    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
    idate
    -0.44
    EndTag
    -0.42
    BeginContext
    -0.42
    pect
    -0.40
    oinette
    -0.39
     pe
    -0.38
    tehen
    -0.38
    ifikant
    -0.37
    brooke
    -0.37
     ex
    -0.37
    POSITIVE LOGITS
     utafitiHapana
    0.87
     تضيفلها
    0.77
    ffilm
    0.66
     vectorielles
    0.63
    Aiheesta
    0.63
    ImageContext
    0.62
    rawDesc
    0.62
     ostavi
    0.61
    MigrationBuilder
    0.60
     scurt
    0.60
    Activations Density 0.030%

    No Known Activations