© 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. 16062
    Prev
    Next
    INDEX
    Explanations

    RT

    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
     Audiodateien
    -0.63
    <bos>
    -0.59
    ItemBackground
    -0.54
    usercontent
    -0.49
    Viungo
    -0.48
    ufer
    -0.47
    "}"
    -0.46
    varlak
    -0.46
     $]$
    -0.44
    hesion
    -0.44
    POSITIVE LOGITS
     radiotherapy
    0.66
    writeFieldEnd
    0.60
     irradiation
    0.59
     IndexPath
    0.59
     Beam
    0.59
     beam
    0.57
     kV
    0.56
    migrationBuilder
    0.56
    yntaxException
    0.56
    ButterKnife
    0.55
    Activations Density 0.089%

    No Known Activations