© 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. 1-CLT-HP
    7. 12081
    Prev
    Next
    INDEX
    Explanations

    cull

    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
    AddTagHelper
    -0.99
     NSCoder
    -0.81
    thorax
    -0.73
    DockStyle
    -0.71
    Autoritní
    -0.71
    principalTable
    -0.70
    InSection
    -0.69
    CloseOperation
    -0.69
    findpost
    -0.69
    parsedMessage
    -0.68
    POSITIVE LOGITS
     timing
    0.45
    jap
    0.44
     tomber
    0.43
    SIGNED
    0.42
    toThrow
    0.42
     deleteById
    0.41
    sel
    0.40
    NOWLEDG
    0.39
     hinzu
    0.39
     préf
    0.39
    Activations Density 0.056%

    No Known Activations