© 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. 0-CLT-HP
    7. 95233
    Prev
    Next
    INDEX
    Explanations

    area

    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
     protoimpl
    -0.66
    GraphicsUnit
    -0.59
    Area
    -0.59
     Area
    -0.57
    ers
    -0.57
     الرياضيه
    -0.56
    DispatchToProps
    -0.54
    IsContent
    -0.52
    ERS
    -0.51
    veness
    -0.51
    POSITIVE LOGITS
     defaultstate
    0.55
     Sni
    0.54
    expliquer
    0.54
     Heard
    0.53
    DockStyle
    0.53
     Telling
    0.52
     Wire
    0.50
     Hedge
    0.50
     Finder
    0.50
     Breeding
    0.50
    Activations Density 0.193%

    No Known Activations