© 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. 5-CLT-HP
    7. 93169
    Prev
    Next
    INDEX
    Explanations

    code

    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
     GoogleFonts
    -0.47
     scolaires
    -0.45
    Atsauces
    -0.45
    Aholisi
    -0.44
    rouvez
    -0.44
    arition
    -0.43
    BeginInit
    -0.41
    onActivityResult
    -0.41
     umane
    -0.39
     négociations
    -0.39
    POSITIVE LOGITS
    Portály
    0.62
     snippetHide
    0.61
     חיצוניים
    0.59
    Tikang
    0.59
    addCriterion
    0.58
    >--}}
    0.57
    expandindo
    0.56
    屏
    0.53
    tagHelperRunner
    0.52
    انيف
    0.52
    Activations Density 0.005%

    No Known Activations