© 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. 77806
    Prev
    Next
    INDEX
    Explanations

    Scientific research

    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
    msgTypes
    -0.46
    idends
    -0.43
    iov
    -0.41
    ьа
    -0.40
    wyd
    -0.40
     Admissions
    -0.39
     Cardona
    -0.38
    AsUp
    -0.38
    pektrum
    -0.38
    LookAnd
    -0.38
    POSITIVE LOGITS
     StatefulWidget
    0.62
     HasFactory
    0.59
    khó
    0.56
    WebElementEntity
    0.54
    "):
    0.53
    TagMode
    0.52
     تضيفلها
    0.51
     ErrIntOverflow
    0.51
    AxisAlignment
    0.50
    WebMethod
    0.50
    Activations Density 0.005%

    No Known Activations