© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1369
    Prev
    Next
    INDEX
    Explanations

    And

    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
     المعيارى
    -0.83
     Мексичка
    -0.77
    ErrUnexpectedEOF
    -0.75
     تضيفلها
    -0.73
    EndGlobalSection
    -0.72
     صوتيه
    -0.71
    AsUp
    -0.70
    uxxxx
    -0.69
    ()]);
    -0.66
     незавершена
    -0.65
    POSITIVE LOGITS
     yet
    0.54
     weeds
    0.52
     the
    0.52
     so
    0.49
    ười
    0.48
    ついに
    0.47
     tumors
    0.47
     obstinate
    0.47
     skep
    0.45
     legends
    0.44
    Activations Density 0.000%

    No Known Activations