© 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. 14876
    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
     defaultstate
    -0.57
    Amicalement
    -0.54
    BeginContext
    -0.52
    
    -0.52
    jointe
    -0.52
     ostavi
    -0.51
    MergeFrom
    -0.50
    )?;
    -0.50
     to
    -0.49
    Przypisy
    -0.49
    POSITIVE LOGITS
    Tembelea
    0.71
     prioritizing
    0.63
     how
    0.63
     where
    0.62
     ktorí
    0.61
    where
    0.60
     conserving
    0.57
     utilising
    0.56
    RenderAtEndOf
    0.55
    who
    0.55
    Activations Density 0.005%

    No Known Activations