© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41866
    Prev
    Next
    INDEX
    Explanations

    refraction

    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
    d
    -0.56
     tender
    -0.52
    ness
    -0.50
    XmlAccessType
    -0.50
    data
    -0.49
    ostante
    -0.48
    qvarna
    -0.48
     AssemblyCulture
    -0.44
    ghed
    -0.44
     dig
    -0.44
    POSITIVE LOGITS
     Diſ
    0.84
     Eſ
    0.83
     itſelf
    0.78
    Pautan
    0.77
     myſelf
    0.76
     Monfieur
    0.76
     becauſe
    0.74
     Theſe
    0.72
     Majefty
    0.71
     ―――――
    0.70
    Activations Density 0.281%

    No Known Activations