© 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. 98121
    Prev
    Next
    INDEX
    Explanations

    actions/achievements

    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
     ProtoMessage
    -0.68
     تانيه
    -0.64
     صوتيه
    -0.63
     Normdatei
    -0.62
    kháu
    -0.61
     BorderRadius
    -0.60
    prefixer
    -0.59
    chooser
    -0.58
    CloseOperation
    -0.57
     الحره
    -0.57
    POSITIVE LOGITS
     far
    0.71
     if
    0.70
     more
    0.69
     eventually
    0.63
     faster
    0.60
     IF
    0.59
     less
    0.59
    eventually
    0.59
     quicker
    0.56
     Eventually
    0.56
    Activations Density 0.002%

    No Known Activations