© 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. 4-CLT-HP
    7. 5042
    Prev
    Next
    INDEX
    Explanations

    quotation mark and period

    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
     Once
    -0.46
     The
    -0.45
     Spreading
    -0.45
     Moreover
    -0.44
     Whether
    -0.43
     Subsequent
    -0.42
     Prior
    -0.40
     A
    -0.40
     However
    -0.39
     Also
    -0.39
    POSITIVE LOGITS
     well
    0.71
    VersionUID
    0.67
     raiſ
    0.66
    abestanden
    0.66
    bewerken
    0.65
     pleaſure
    0.65
    SourceChecksum
    0.64
    createServer
    0.64
    ScopeManager
    0.63
     preprint
    0.63
    Activations Density 0.009%

    No Known Activations