© 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. 40647
    Prev
    Next
    INDEX
    Explanations

    to

    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
     the
    -0.92
     an
    -0.70
     and
    -0.70
     a
    -0.69
     its
    -0.63
    ,
    -0.62
     contracting
    -0.61
     those
    -0.60
     any
    -0.59
    standing
    -0.58
    POSITIVE LOGITS
    #
    0.97
    DockStyle
    0.95
    __':
    0.82
     uſe
    0.75
    __":
    0.73
    prepareStatement
    0.70
     WebDriverWait
    0.70
    ihnachts
    0.69
     ſind
    0.69
     Audiodateien
    0.69
    Activations Density 0.121%

    No Known Activations