© 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. 0-CLT-HP
    7. 95175
    Prev
    Next
    INDEX
    Explanations

    copper

    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
     cup
    -1.60
     Cup
    -1.46
    Cu
    -1.45
    cup
    -1.44
    Cup
    -1.44
     cu
    -1.38
     CUP
    -1.34
     Cu
    -1.33
    CUP
    -1.30
     copper
    -1.28
    POSITIVE LOGITS
    IBarButtonItem
    0.72
    angliski
    0.69
    ed
    0.63
     Efq
    0.63
    })));
    0.61
     betweenstory
    0.59
     raiſ
    0.57
    posables
    0.57
    ñores
    0.56
    IntoConstraints
    0.56
    Activations Density 0.050%

    No Known Activations