© 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. 10126
    Prev
    Next
    INDEX
    Explanations

    flaming

    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
     referenties
    -0.80
    Datuak
    -0.68
     وتسجيلات
    -0.65
    SourceChecksum
    -0.64
     تضيفلها
    -0.63
     Himo
    -0.60
     volon
    -0.58
    ConstraintMaker
    -0.58
     fermés
    -0.57
     réfugiés
    -0.56
    POSITIVE LOGITS
    NSIndexPath
    0.53
    endphp
    0.50
    dziew
    0.50
    LookAnd
    0.46
     Cous
    0.46
    avy
    0.44
    octa
    0.44
    rat
    0.44
     StatefulWidget
    0.43
    agie
    0.43
    Activations Density 0.103%

    No Known Activations