© 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. 94330
    Prev
    Next
    INDEX
    Explanations

    code and image references

    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
     تانيه
    -0.73
    المراجع
    -0.68
    ]--;
    -0.67
    */),
    -0.63
     CreateTagHelper
    -0.63
     EconPapers
    -0.61
     بيها
    -0.61
    KommentareTeilen
    -0.59
     Мексичка
    -0.58
    chairs
    -0.57
    POSITIVE LOGITS
     comprado
    0.46
     valmis
    0.43
    Capa
    0.42
    '
    0.41
     regionale
    0.41
    Pinned
    0.40
    \'
    0.39
    “
    0.39
     puol
    0.39
    Inserted
    0.39
    Activations Density 0.003%

    No Known Activations