© 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. 4-CLT-HP
    7. 699
    Prev
    Next
    INDEX
    Explanations

    of

    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
     that
    -0.59
     the
    -0.44
    unsplash
    -0.43
     счита
    -0.42
    valuations
    -0.42
    muss
    -0.42
     bangsa
    -0.42
     Son
    -0.42
    setState
    -0.41
    claims
    -0.41
    POSITIVE LOGITS
     effectiveness
    0.76
     efficacy
    0.68
    Tembelea
    0.68
     дописавши
    0.65
    ContextHolder
    0.63
    ########.
    0.63
    where
    0.62
     where
    0.62
     Effectiveness
    0.61
     usefulness
    0.60
    Activations Density 0.007%

    No Known Activations