© 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. 3897
    Prev
    Next
    INDEX
    Explanations

    petition

    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
    ]--;
    -0.50
    --){
    -0.49
    Xna
    -0.47
     trap
    -0.44
    \{\\
    -0.44
     doInBackground
    -0.41
    にほん
    -0.40
     makeStyles
    -0.40
     haircut
    -0.39
    TagMode
    -0.39
    POSITIVE LOGITS
     vägen
    0.66
     تضيفلها
    0.65
     the
    0.63
     auroit
    0.61
     validés
    0.60
     BorderRadius
    0.60
     betweenstory
    0.59
     uska
    0.58
     ویکی‌پدیای
    0.58
    Autoritní
    0.58
    Activations Density 0.004%

    No Known Activations