© 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. 1-CLT-HP
    7. 630
    Prev
    Next
    INDEX
    Explanations

    separate

    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
     separator
    -1.21
     Separator
    -1.03
     separators
    -0.94
     separations
    -0.86
     separation
    -0.84
     separating
    -0.82
    separation
    -0.79
     seper
    -0.78
     Separ
    -0.78
    separator
    -0.77
    POSITIVE LOGITS
     out
    0.69
     saites
    0.53
    out
    0.53
    mergeFrom
    0.53
    Out
    0.52
     Out
    0.51
    Попис
    0.47
     demografica
    0.46
     säll
    0.44
     mål
    0.43
    Activations Density 0.160%

    No Known Activations