© 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. 97787
    Prev
    Next
    INDEX
    Explanations

    math calculations

    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
    Personensuche
    -0.57
    WriteLiteral
    -0.54
    findpost
    -0.49
    rupal
    -0.49
     CreateTagHelper
    -0.49
    photobucket
    -0.48
    ListItemIcon
    -0.48
    OGND
    -0.48
     uska
    -0.47
    llt
    -0.47
    POSITIVE LOGITS
    EnableWeb
    0.61
     }{@
    0.59
    Subclass
    0.59
     strå
    0.58
    quatre
    0.58
     deberes
    0.57
    #
    0.56
     isolé
    0.56
     révélé
    0.55
    CardBody
    0.54
    Activations Density 0.095%

    No Known Activations