© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38682
    Prev
    Next
    INDEX
    Explanations

    thal

    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
     thal
    -0.59
     negroes
    -0.54
    buttonShape
    -0.52
     Everglades
    -0.52
     ͡°
    -0.51
     prophylaxis
    -0.51
    s
    -0.50
     archaeology
    -0.50
     Year
    -0.49
     Rockies
    -0.49
    POSITIVE LOGITS
    apist
    0.60
    ecap
    0.55
    ModelAdmin
    0.55
    IsContent
    0.52
    WireFormatLite
    0.52
    ricus
    0.52
    WindowConstants
    0.50
     متعلقه
    0.49
     Audiodateien
    0.48
    קישורים
    0.48
    Activations Density 0.080%

    No Known Activations