© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73516
    Prev
    Next
    INDEX
    Explanations

    stream

    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
     وتسجيلات
    -0.71
    tanleria
    -0.62
     ivelany
    -0.62
    multer
    -0.60
     Efq
    -0.60
    LEncoder
    -0.59
     Jefus
    -0.58
    visuel
    -0.57
    ɵɵ
    -0.57
    ensión
    -0.57
    POSITIVE LOGITS
     stream
    1.01
     streams
    0.93
     Streams
    0.85
     Stream
    0.82
    stream
    0.78
     STREAM
    0.73
    Stream
    0.70
    STREAM
    0.68
    Streams
    0.66
     ver
    0.63
    Activations Density 0.000%

    No Known Activations