© 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. 1-CLT-HP
    7. 15199
    Prev
    Next
    INDEX
    Explanations

    strength

    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
     strength
    -1.56
    strength
    -1.27
     Strength
    -1.23
    Strength
    -1.14
     STRENGTH
    -1.02
     strengths
    -0.96
     Strengths
    -0.75
    STRENGTH
    -0.72
     fortaleza
    -0.71
     streng
    -0.69
    POSITIVE LOGITS
     '\\;'
    0.98
     EconPapers
    0.97
     فريبيس
    0.92
    
    0.92
     Roskov
    0.88
    ."));
    0.85
     Pingback
    0.83
    parsedMessage
    0.83
     désolés
    0.82
     مرئيه
    0.81
    Activations Density 0.003%

    No Known Activations