© 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. 4-CLT-HP
    7. 3089
    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
    ⓘ
    -0.69
     disambiguazione
    -0.69
    openzeppelin
    -0.63
    simpleType
    -0.63
    Aiheesta
    -0.61
     ISNI
    -0.57
    nexo
    -0.56
    Jegyzetek
    -0.56
    iverr
    -0.55
    migrationBuilder
    -0.54
    POSITIVE LOGITS
     MERCHANTABILITY
    0.57
    bootstrapcdn
    0.51
    chappen
    0.50
     Inhalten
    0.48
    otine
    0.44
     gynhyrchwyd
    0.43
     most
    0.43
    cshtml
    0.43
     magasiner
    0.42
    hyrchwyd
    0.42
    Activations Density 0.003%

    No Known Activations