© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 731
    Prev
    Next
    INDEX
    Explanations

    internet posts

    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
    CodeAttribute
    -0.80
    Personendaten
    -0.66
    enumi
    -0.65
    findpost
    -0.63
    ⓘ
    -0.57
    MigrationBuilder
    -0.57
    tahui
    -0.57
     Beſ
    -0.56
    EMBLE
    -0.56
     ویکی‌پدیای
    -0.55
    POSITIVE LOGITS
     is
    0.71
     was
    0.54
     are
    0.50
    .
    0.48
     merupakan
    0.44
     kasarigan
    0.44
     represents
    0.43
     serves
    0.43
    exitRule
    0.43
     instead
    0.42
    Activations Density 0.000%

    No Known Activations