© 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. 91158
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    setof
    -0.73
    CodeAttribute
    -0.69
     Himo
    -0.69
    følgelig
    -0.68
    oa̍t
    -0.67
     estekak
    -0.66
    TypedDataSet
    -0.66
     ostavi
    -0.65
     betweenstory
    -0.65
    SharedDtor
    -0.64
    POSITIVE LOGITS
     and
    0.62
     their
    0.49
     up
    0.47
    DoesNotExist
    0.42
    ,
    0.42
    uoto
    0.41
    up
    0.40
     AssemblyCulture
    0.40
    criar
    0.38
     at
    0.37
    Activations Density 0.001%

    No Known Activations