© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41831
    Prev
    Next
    INDEX
    Explanations

    cables and interference

    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
     column
    -0.99
    column
    -0.79
    ChildScrollView
    -0.67
     للمعارف
    -0.65
    Column
    -0.63
    %\[
    -0.59
     regime
    -0.59
    taining
    -0.58
     colonne
    -0.58
     Column
    -0.58
    POSITIVE LOGITS
    s
    0.72
     disponibilités
    0.62
     nadar
    0.52
    AndEndTag
    0.51
    lji
    0.49
     coser
    0.49
     nacionais
    0.48
     nervosa
    0.48
     Wikidata
    0.47
     nostru
    0.47
    Activations Density 0.086%

    No Known Activations