© 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. 0-CLT-HP
    7. 43166
    Prev
    Next
    INDEX
    Explanations

    decimal

    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
     decimal
    -1.09
     decimals
    -0.78
     inflammation
    -0.76
     Decimal
    -0.75
    ########.
    -0.73
     Inflammation
    -0.66
     Continue
    -0.66
     degeneration
    -0.66
    decimal
    -0.65
    Decimal
    -0.63
    POSITIVE LOGITS
    VolleyError
    0.64
    ंदीखरीदारी
    0.59
    i
    0.59
    e
    0.55
     alive
    0.54
    ApiRequest
    0.54
     کش
    0.52
    el
    0.52
    present
    0.52
     tuong
    0.49
    Activations Density 0.182%

    No Known Activations