© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16131
    Prev
    Next
    INDEX
    Explanations

    disabled

    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
    Negative Logits
     مرئيه
    -0.75
    adpleegd
    -0.69
    CppMethod
    -0.67
    Rujuakan
    -0.67
     ainfi
    -0.66
     clô
    -0.64
     étoit
    -0.64
     étoient
    -0.63
    UnknownFields
    -0.61
     Disabled
    -0.61
    POSITIVE LOGITS
    #+#
    0.63
     charset
    0.56
     MainAxisSize
    0.55
    s
    0.50
    bs
    0.50
    bootstrapcdn
    0.47
     Ca
    0.46
    dot
    0.46
    mand
    0.45
    Auto
    0.45
    Activations Density 0.026%

    No Known Activations