© 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. 4-CLT-HP
    7. 3099
    Prev
    Next
    INDEX
    Explanations

    Theore

    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
     ujednoznacz
    -0.63
     Phari
    -0.62
    filé
    -0.50
    bietern
    -0.49
    таратура
    -0.49
     uva
    -0.48
     Bonner
    -0.48
     Rosenthal
    -0.48
     prepared
    -0.48
     flown
    -0.48
    POSITIVE LOGITS
    see
    0.77
    SEE
    0.58
    AxisAlignment
    0.57
     SEE
    0.56
    seeing
    0.51
     MainAxisSize
    0.49
    Rhestr
    0.48
    sem
    0.48
    seer
    0.48
    ViewFeatures
    0.48
    Activations Density 0.000%

    No Known Activations