© 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. 5-CLT-HP
    7. 6173
    Prev
    Next
    INDEX
    Explanations

    doi

    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
     Draw
    -0.51
     Niz
    -0.48
    REMARKS
    -0.48
     draw
    -0.47
    announcement
    -0.47
     pitch
    -0.46
     letter
    -0.46
     panel
    -0.46
     call
    -0.45
     announcement
    -0.44
    POSITIVE LOGITS
     JSTOR
    0.68
     Normdatei
    0.65
    EndContext
    0.63
    SharedDtor
    0.62
    脚注の使い方
    0.62
    PYX
    0.62
     مرئيه
    0.62
     JADX
    0.62
    riterien
    0.61
    CppMethod
    0.59
    Activations Density 0.011%

    No Known Activations