© 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. 5-CLT-HP
    7. 94272
    Prev
    Next
    INDEX
    Explanations

    sea creatures

    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
     оригіналу
    -0.60
    __*/
    -0.52
    recht
    -0.49
     DbSet
    -0.47
     Вікі
    -0.46
    }`).
    -0.45
    }]{
    -0.43
    NER
    -0.42
    ("")]
    -0.42
     choking
    -0.42
    POSITIVE LOGITS
    findpost
    0.73
    Portale
    0.57
    ReusableCell
    0.55
    ans
    0.53
    pherals
    0.52
     avancé
    0.49
    putan
    0.49
    KommentareTeilen
    0.48
     LEYENDO
    0.48
    Bronnen
    0.48
    Activations Density 0.000%

    No Known Activations