© 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. 38666
    Prev
    Next
    INDEX
    Explanations

    couple

    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
     réguli
    -0.82
     ErrIntOverflow
    -0.79
    цездатний
    -0.76
    Rüyada
    -0.75
     tartalomajánló
    -0.75
    Попис
    -0.75
     cérami
    -0.72
     BoxFit
    -0.72
    ThroughAttribute
    -0.71
     المعيارى
    -0.71
    POSITIVE LOGITS
     fat
    0.42
     yet
    0.42
     thin
    0.40
    ắt
    0.40
     up
    0.39
    zyj
    0.39
     plans
    0.39
     reproduce
    0.39
    dci
    0.39
     FAT
    0.38
    Activations Density 0.056%

    No Known Activations