© 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. 5292
    Prev
    Next
    INDEX
    Explanations

    mothers

    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
     للاسماء
    -0.66
     lèvres
    -0.64
     avoient
    -0.63
     étoit
    -0.60
    はじめに
    -0.59
     enfans
    -0.58
     récents
    -0.58
     étoient
    -0.58
    +:+
    -0.57
    ]').
    -0.57
    POSITIVE LOGITS
    ly
    0.59
     monkey
    0.58
    ing
    0.58
     dog
    0.58
     bear
    0.56
    hood
    0.56
     dogs
    0.55
     bird
    0.55
     animals
    0.54
     animal
    0.54
    Activations Density 0.001%

    No Known Activations