© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 75127
    Prev
    Next
    INDEX
    Explanations

    Business, legal, code

    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
    PerformLayout
    -0.82
     دیکھیے
    -0.80
     cherchés
    -0.77
     समीक्षाओं
    -0.77
    NUMX
    -0.75
    UnusedPrivate
    -0.74
    afficheront
    -0.73
    Referencie
    -0.72
     Exacts
    -0.68
     wireType
    -0.68
    POSITIVE LOGITS
     share
    0.59
     market
    0.56
    loài
    0.47
    ot
    0.46
     livet
    0.45
     raise
    0.45
     Market
    0.43
     normal
    0.41
    market
    0.41
    oten
    0.40
    Activations Density 0.002%

    No Known Activations