© 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. 5-CLT-HP
    7. 91567
    Prev
    Next
    INDEX
    Explanations

    not

    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
     chi̍t
    -0.68
     have
    -0.64
     disambiguazione
    -0.63
     الرخصة
    -0.62
    Pautan
    -0.62
    Predecesor
    -0.61
     puisse
    -0.60
     Normdatei
    -0.60
    ftagPool
    -0.59
    EndContext
    -0.57
    POSITIVE LOGITS
     worth
    0.62
     enough
    0.59
     quite
    0.58
     so
    0.57
     assez
    0.56
     optimal
    0.54
     ready
    0.54
     commerciali
    0.53
     sure
    0.52
     a
    0.52
    Activations Density 0.004%

    No Known Activations