© 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. 1943
    Prev
    Next
    INDEX
    Explanations

    intricate situations

    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
     complex
    -1.80
    complex
    -1.77
     Complex
    -1.66
    Complex
    -1.59
     complicated
    -1.57
     complejos
    -1.48
     complexe
    -1.44
     COMPLEX
    -1.44
    complicated
    -1.43
     compleja
    -1.41
    POSITIVE LOGITS
    IntoConstraints
    0.88
    tvguidetime
    0.71
    tly
    0.68
    eded
    0.67
     Empieza
    0.67
     Efq
    0.67
    TypedDataSet
    0.66
    ities
    0.64
    StoryboardSegue
    0.63
    ually
    0.61
    Activations Density 0.076%

    No Known Activations