© 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. 15324
    Prev
    Next
    INDEX
    Explanations

    issues and solutions

    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
    StoryboardSegue
    -0.79
    AutoScale
    -0.75
    UseVisualStyle
    -0.75
     EconPapers
    -0.73
    adaptiveStyles
    -0.73
    Portale
    -0.71
    InputBorder
    -0.71
    WithFormat
    -0.70
    ConstraintMaker
    -0.67
    AMPLE
    -0.66
    POSITIVE LOGITS
    정
    0.40
     stav
    0.40
     bew
    0.40
     blanches
    0.38
    enne
    0.38
    jwa
    0.37
    {#
    0.37
    dees
    0.37
     linee
    0.37
     espec
    0.36
    Activations Density 0.006%

    No Known Activations