© 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. 1470
    Prev
    Next
    INDEX
    Explanations

    uris

    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
    nis
    -0.75
    uris
    -0.73
    atia
    -0.69
    OPS
    -0.68
    hoon
    -0.66
    ala
    -0.66
    ops
    -0.61
    URI
    -0.60
    uri
    -0.60
     Hawk
    -0.58
    POSITIVE LOGITS
     énergé
    0.76
     Majefty
    0.73
     reaſon
    0.73
     pleaſure
    0.72
     reafon
    0.71
     normaux
    0.69
     poffible
    0.69
     Anſ
    0.68
     Houſe
    0.67
     Perſ
    0.65
    Activations Density 0.057%

    No Known Activations