© 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. 0-CLT-HP
    7. 97349
    Prev
    Next
    INDEX
    Explanations

    orally

    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
     vectorielle
    -0.74
     vectorielles
    -0.66
     crystallized
    -0.64
     vectorstock
    -0.59
     crystall
    -0.59
     grecque
    -0.59
     yerde
    -0.58
     féminine
    -0.58
     compréhen
    -0.58
     japonaise
    -0.58
    POSITIVE LOGITS
     كومونز
    0.76
    UrlResolution
    0.74
    Portail
    0.73
     архивлан
    0.67
    ="@+
    0.65
     AssemblyCompany
    0.63
     ModelExpression
    0.63
    homonymie
    0.61
    cimientos
    0.60
    ########.
    0.59
    Activations Density 1.391%

    No Known Activations