© 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. 4764
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     utafitiHapana
    -0.71
     للمعارف
    -0.63
     يتيمه
    -0.56
     intptr
    -0.56
    protoimpl
    -0.53
     itſelf
    -0.53
     متعلقه
    -0.53
     تانيه
    -0.53
     بيها
    -0.51
    ImageContext
    -0.51
    POSITIVE LOGITS
     
    0.82
    1
    0.57
     $
    0.55
    3
    0.54
    2
    0.54
    @[+][
    0.53
    8
    0.53
    fel
    0.53
    5
    0.52
    fan
    0.51
    Activations Density 0.009%

    No Known Activations