© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97468
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     “
    -1.25
    to
    -0.79
    or
    -0.78
    on
    -0.75
    s
    -0.74
    de
    -0.69
    at
    -0.68
    time
    -0.68
    li
    -0.67
    f
    -0.66
    POSITIVE LOGITS
    '."
    1.00
     Theſe
    0.98
     Efq
    0.94
     ...'
    0.94
    '
    0.93
     myſelf
    0.91
    .''
    0.89
    '...
    0.88
     Chriftian
    0.88
    ."</
    0.88
    Activations Density 0.015%

    No Known Activations