© 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. 5-CLT-HP
    7. 93705
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    पया
    -0.85
    HasBeenSet
    -0.79
    ')):
    -0.71
    IVEREF
    -0.69
    Източници
    -0.67
    .},
    -0.66
     CURIAM
    -0.65
     ब्रेकडाउन
    -0.65
    TestingModule
    -0.64
    تقاوى
    -0.64
    POSITIVE LOGITS
     would
    0.52
    ↵
    0.50
    c
    0.48
     may
    0.47
     finally
    0.47
    enumi
    0.46
     investigated
    0.45
     is
    0.45
     digs
    0.44
     was
    0.44
    Activations Density 0.004%

    No Known Activations