© 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. 5-CLT-HP
    7. 92606
    Prev
    Next
    INDEX
    Explanations

    shadow

    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
    AccessorTable
    -0.69
    MeasureSpec
    -0.67
    تقاوى
    -0.65
     Lordships
    -0.63
     beginnetje
    -0.63
    \{\\
    -0.61
     Савезне
    -0.60
    NOPQRST
    -0.60
     незавершена
    -0.59
     gynhyrchwyd
    -0.59
    POSITIVE LOGITS
     out
    0.52
     either
    0.43
    $=\
    0.41
     Out
    0.41
     же
    0.40
    Rüyada
    0.40
     run
    0.39
    skjaer
    0.39
    UserScript
    0.38
    Palmarès
    0.38
    Activations Density 0.006%

    No Known Activations