© 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. 0-CLT-HP
    7. 94223
    Prev
    Next
    INDEX
    Explanations

    apostrophes/hyphens

    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
    ‘
    -0.78
    ·
    -0.60
    o
    -0.56
    ar
    -0.54
    •
    -0.51
    
    -0.48
    ・
    -0.46
    ne
    -0.46
    ‐
    -0.46
     “
    -0.45
    POSITIVE LOGITS
    SBATCH
    1.20
     Мексичка
    1.17
    ArrowToggle
    1.15
    LookAnd
    1.13
    ]))
    1.02
    +#+#
    1.02
     <=",
    1.02
    tvguidetime
    1.02
    parsedMessage
    1.02
    DockStyle
    1.00
    Activations Density 1.158%

    No Known Activations