© 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. 1-CLT-HP
    7. 11497
    Prev
    Next
    INDEX
    Explanations

    semantics and "us"

    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
     Witness
    -0.45
    endphp
    -0.43
    Witness
    -0.41
     oídos
    -0.41
    parms
    -0.40
    msleep
    -0.40
    ING
    -0.39
    олові
    -0.39
     متعلقه
    -0.38
    expandindo
    -0.38
    POSITIVE LOGITS
    MigrationBuilder
    0.78
    DoubleQuotes
    0.73
     nawr
    0.70
    DebuggerNonUser
    0.69
     flooding
    0.66
    SharedDtor
    0.64
     gynhyrchwyd
    0.64
    rrggbb
    0.63
     thawing
    0.60
    Билгалдахарш
    0.59
    Activations Density 0.013%

    No Known Activations