© 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. 2395
    Prev
    Next
    INDEX
    Explanations

    equipped

    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
    ########.
    -0.79
    enumi
    -0.65
    afficheront
    -0.56
    ftagPool
    -0.54
    lewati
    -0.53
     kautta
    -0.53
     éte
    -0.53
     éti
    -0.50
     commerciaux
    -0.50
    preuve
    -0.50
    POSITIVE LOGITS
     متعلقه
    0.71
     gills
    0.56
    VIAF
    0.56
    styleUrls
    0.55
     tweezers
    0.54
     tiny
    0.53
     sharp
    0.52
     killers
    0.52
     ingenious
    0.51
     amazing
    0.50
    Activations Density 0.002%

    No Known Activations