© 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. 5-CLT-HP
    7. 4220
    Prev
    Next
    INDEX
    Explanations

    durations in experiments

    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
    tagHelperRunner
    -1.02
     HasFactory
    -0.87
    BagConstraints
    -0.83
     Efq
    -0.82
     RoutedEventArgs
    -0.78
     NavController
    -0.78
    })();
    -0.78
     saites
    -0.78
     NSCoder
    -0.78
     Diſ
    -0.77
    POSITIVE LOGITS
     and
    0.66
     (
    0.60
    ,
    0.60
     e
    0.46
     earlier
    0.41
     more
    0.40
     early
    0.40
     continuous
    0.40
     during
    0.36
     but
    0.35
    Activations Density 0.045%

    No Known Activations