© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93349
    Prev
    Next
    INDEX
    Explanations

    ully

    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
    ully
    -1.02
    medical
    -0.85
     médicale
    -0.62
     termica
    -0.60
     FUNERAL
    -0.57
    ULLY
    -0.55
     Funeral
    -0.54
    Funeral
    -0.51
     medica
    -0.51
    gule
    -0.51
    POSITIVE LOGITS
    rungsseite
    0.67
    ArgsConstructor
    0.66
    +#+#
    0.61
    tovers
    0.59
     artikkeli
    0.58
     home
    0.58
    fastjson
    0.58
    UIControlState
    0.57
    StructEnd
    0.57
    жте
    0.56
    Activations Density 0.091%

    No Known Activations