© 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. 90887
    Prev
    Next
    INDEX
    Explanations

    medical/legal texts

    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
     trans
    -0.79
    bir
    -0.75
     imposed
    -0.71
     and
    -0.63
     imposing
    -0.60
    inf
    -0.59
    pen
    -0.57
     te
    -0.55
     bir
    -0.55
    <eos>
    -0.55
    POSITIVE LOGITS
     myſelf
    1.13
     Efq
    1.06
     Houſe
    1.00
     themſelves
    0.98
     Monfieur
    0.95
     Theſe
    0.94
     itſelf
    0.94
     auffi
    0.93
     doubtnut
    0.93
     houſe
    0.91
    Activations Density 1.135%

    No Known Activations