© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92470
    Prev
    Next
    INDEX
    Explanations

    literature

    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
    enumii
    -1.07
     Literature
    -0.93
    ConstraintMaker
    -0.89
    literature
    -0.88
     literature
    -0.86
    AddTagHelper
    -0.79
    enumi
    -0.79
     acorns
    -0.76
    DockStyle
    -0.75
     literatura
    -0.74
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.63
    ות
    0.50
     depend
    0.48
    мыш
    0.46
    strip
    0.44
     MY
    0.44
     van
    0.43
    stdin
    0.43
    pois
    0.42
     Ro
    0.42
    Activations Density 0.029%

    No Known Activations