© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94131
    Prev
    Next
    INDEX
    Explanations

    Cry

    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
    cry
    -0.78
    Cry
    -0.76
    CRY
    -0.68
     AssemblyTitle
    -0.67
     disambiguazione
    -0.60
     Cry
    -0.60
     <<<<<<<<<<<<<<
    -0.59
     الرخصة
    -0.57
    GLenum
    -0.56
    adaş
    -0.55
    POSITIVE LOGITS
    o
    0.84
    e
    0.66
    y
    0.65
    a
    0.57
    i
    0.56
    st
    0.55
    Попис
    0.54
    ی
    0.53
    تقاوى
    0.52
    still
    0.51
    Activations Density 0.161%

    No Known Activations