© 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. 92960
    Prev
    Next
    INDEX
    Explanations

    surgery

    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
    openzeppelin
    -0.59
     recurring
    -0.56
     ويكيميديا
    -0.53
    URLException
    -0.53
     consultato
    -0.52
    cism
    -0.52
    PerformLayout
    -0.49
    Rhestr
    -0.49
    wahati
    -0.48
     Surgeons
    -0.47
    POSITIVE LOGITS
    Hentet
    0.63
    tive
    0.59
    XmlEnum
    0.59
     Roskov
    0.58
    ist
    0.57
     nonatomic
    0.55
    المكان
    0.54
     divides
    0.53
    ider
    0.53
    oder
    0.53
    Activations Density 0.111%

    No Known Activations