© 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. 4923
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    saraba
    -0.76
     resourceCulture
    -0.75
     AssemblyProduct
    -0.74
    complexContent
    -0.74
    󠁢
    -0.68
    şiv
    -0.68
    initComponents
    -0.65
    extAlignment
    -0.65
    AnimationsModule
    -0.64
    FontOfSize
    -0.63
    POSITIVE LOGITS
     is
    0.59
     has
    0.57
    appears
    0.50
    are
    0.48
    has
    0.48
     was
    0.48
     have
    0.47
     are
    0.47
     rezerv
    0.45
     would
    0.45
    Activations Density 0.045%

    No Known Activations