© 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. 75821
    Prev
    Next
    INDEX
    Explanations

    Code and programming language

    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
    šanu
    -0.67
     McDonough
    -0.64
     sauvages
    -0.62
     MacLeod
    -0.60
    davis
    -0.59
    identify
    -0.59
    id
    -0.57
     légale
    -0.57
     polaire
    -0.57
    šanai
    -0.56
    POSITIVE LOGITS
    qrt
    0.46
    PMailer
    0.45
    ConstraintMaker
    0.43
    setVerticalGroup
    0.41
     никого
    0.40
    OrEqual
    0.39
    bonucleic
    0.39
    ьа
    0.39
    avía
    0.39
    uParam
    0.39
    Activations Density 0.000%

    No Known Activations