© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41084
    Prev
    Next
    INDEX
    Explanations

    to

    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
    cinogenicity
    -0.62
    +#+#
    -0.60
     bint
    -0.59
    ajemy
    -0.56
     reformer
    -0.56
     elector
    -0.55
    thorn
    -0.55
     and
    -0.55
     contributor
    -0.54
    riever
    -0.54
    POSITIVE LOGITS
     مشين
    0.69
    RenderAtEndOf
    0.66
    
    0.66
    Enllaces
    0.65
     externi
    0.62
     Hence
    0.61
     hence
    0.60
    ">//
    0.60
    tagHelperRunner
    0.59
    AutoScaleMode
    0.58
    Activations Density 0.042%

    No Known Activations