© 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. 93877
    Prev
    Next
    INDEX
    Explanations

    was

    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
     médicaux
    -0.75
     tarko
    -0.74
     للاسماء
    -0.73
     aikaa
    -0.73
     supérieurs
    -0.71
     spéciaux
    -0.71
     rumahnya
    -0.71
     fidé
    -0.69
     destinées
    -0.69
     étoient
    -0.69
    POSITIVE LOGITS
     found
    0.56
    Found
    0.53
     reprodu
    0.49
    found
    0.48
     evalu
    0.47
     roten
    0.47
     bacterio
    0.47
    nste
    0.46
     foc
    0.44
     odonto
    0.44
    Activations Density 0.187%

    No Known Activations