© 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. 20-CLT-HP
    7. 76382
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    np_max-act-logits · 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
     betweenstory
    -0.82
     صوتيه
    -0.69
     âmes
    -0.66
     समीक्षाएं
    -0.64
    setVerticalGroup
    -0.64
    endphp
    -0.63
     enfans
    -0.63
    EndGlobalSection
    -0.63
    CompilerServices
    -0.62
     esprits
    -0.62
    POSITIVE LOGITS
     amist
    0.45
    #__
    0.42
    comy
    0.41
     nage
    0.40
    ocino
    0.38
    Xiv
    0.38
    لاق
    0.37
    Vog
    0.37
    pro
    0.37
    änn
    0.37
    Activations Density 0.002%

    No Known Activations