© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9867
    Prev
    Next
    INDEX
    Explanations

    cables and falling hazards

    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
    ArgsConstructor
    -0.64
     Himself
    -0.52
    GEBURTSDATUM
    -0.49
    Magento
    -0.49
     CommonModule
    -0.48
    Clik
    -0.48
     faſt
    -0.47
     meis
    -0.47
    He
    -0.47
     niv
    -0.47
    POSITIVE LOGITS
    +#+#
    0.60
    ocity
    0.59
    躇
    0.56
    ]='\
    0.51
    )++;
    0.48
    MessageOf
    0.48
    checks
    0.48
    ioutil
    0.47
    Географија
    0.47
    Zunanje
    0.46
    Activations Density 0.011%

    No Known Activations