© 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. 92707
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     '\\;'
    -0.80
    Chham
    -0.68
    IsMutable
    -0.61
     referenties
    -0.60
    elemField
    -0.60
    ="@+
    -0.56
     autorytatywna
    -0.56
     @}
    -0.56
    UrlEncoded
    -0.56
    ChildIndex
    -0.55
    POSITIVE LOGITS
     miles
    0.62
     therefrom
    0.54
    시오
    0.47
     acres
    0.46
    km
    0.46
     Miles
    0.46
    miles
    0.46
    LikeLike
    0.45
    Equals
    0.44
     hr
    0.44
    Activations Density 0.019%

    No Known Activations