© 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. 1-CLT-HP
    7. 15386
    Prev
    Next
    INDEX
    Explanations

    add

    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
     adding
    -0.74
     add
    -0.70
     Adding
    -0.67
    Adding
    -0.66
     added
    -0.66
     adds
    -0.63
     Add
    -0.60
    adding
    -0.59
     ajout
    -0.58
    add
    -0.56
    POSITIVE LOGITS
     up
    0.80
    ItemBackground
    0.69
     vastaan
    0.68
    sidemargin
    0.63
     linkovi
    0.60
     snippetHide
    0.60
     autorytatywna
    0.59
     lisäksi
    0.58
     unknownFields
    0.58
    oneofs
    0.58
    Activations Density 0.014%

    No Known Activations