© 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. 0-CLT-HP
    7. 92859
    Prev
    Next
    INDEX
    Explanations

    TO

    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
    TO
    -0.90
    enumii
    -0.84
    cost
    -0.75
     OFDb
    -0.67
    enumi
    -0.66
     Tod
    -0.60
    toe
    -0.60
    Tod
    -0.59
     ModelExpression
    -0.59
     שוליים
    -0.57
    POSITIVE LOGITS
     lenker
    0.69
    matically
    0.52
    úsqueda
    0.50
    ingly
    0.49
    ily
    0.48
    ništvo
    0.48
    tly
    0.48
    urally
    0.48
     ISNI
    0.47
    redge
    0.47
    Activations Density 0.201%

    No Known Activations