© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 6102
    Prev
    Next
    INDEX
    Explanations

    technical/coding issues

    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
    TagMode
    -0.89
     vectorielles
    -0.58
    <bos>
    -0.56
     quelcon
    -0.56
    setVerticalGroup
    -0.54
    UnusedPrivate
    -0.52
    dymyr
    -0.52
     đâu
    -0.52
    AndEndTag
    -0.51
     feroit
    -0.51
    POSITIVE LOGITS
    .
    0.79
    脚注の使い方
    0.60
    󠁿
    0.54
     indeed
    0.53
    ).
    0.52
    ).
    0.52
    》.
    0.51
    SharedDtor
    0.51
    ≦)
    0.50
    ."));
    0.48
    Activations Density 0.000%

    No Known Activations