© 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. 94743
    Prev
    Next
    INDEX
    Explanations

    focused

    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
     الحره
    -0.64
     passés
    -0.52
     judiciaire
    -0.52
    appartamento
    -0.51
    Vege
    -0.51
    zzá
    -0.50
    illères
    -0.49
     heen
    -0.49
     époux
    -0.48
     stället
    -0.48
    POSITIVE LOGITS
     on
    0.63
     upon
    0.58
    unately
    0.57
    ModelSerializer
    0.56
    liferay
    0.56
    SpringRunner
    0.54
     uska
    0.53
     around
    0.52
    下载附件
    0.50
    󠁣
    0.50
    Activations Density 0.002%

    No Known Activations