© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76042
    Prev
    Next
    INDEX
    Explanations

    Punctuation/possessives

    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
    -0.73
     Оно
    -0.71
    ftagPool
    -0.67
     AssemblyProduct
    -0.66
    herself
    -0.65
    himself
    -0.63
    ็จ
    -0.63
    和我
    -0.63
     Itself
    -0.63
    aragus
    -0.62
    POSITIVE LOGITS
    ’
    1.11
    '
    1.06
     their
    0.87
    $'
    0.86
    \'
    0.77
    }'
    0.68
    ´
    0.65
     的
    0.61
     your
    0.61
    ]'
    0.60
    Activations Density 0.012%

    No Known Activations