© 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. 752
    Prev
    Next
    INDEX
    Explanations

    though

    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
     I
    -0.50
     my
    -0.37
    Datuak
    -0.35
     conosci
    -0.35
    見た
    -0.35
    Personensuche
    -0.35
    kso
    -0.34
    ScopeManager
    -0.34
     you
    -0.33
     spirits
    -0.33
    POSITIVE LOGITS
    ViewFeatures
    0.77
    DoubleQuotes
    0.73
     autorytatywna
    0.65
     userSchema
    0.61
    anasia
    0.60
     ẞ
    0.59
     <",
    0.59
    atrician
    0.58
     adjoint
    0.58
     Anſ
    0.57
    Activations Density 0.009%

    No Known Activations