© 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. 0-CLT-HP
    7. 95600
    Prev
    Next
    INDEX
    Explanations

    Change of state/location

    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
    -------
    -0.47
    ArrayOf
    -0.47
    zeug
    -0.41
    ness
    -0.40
    ogue
    -0.40
    wise
    -0.38
    momix
    -0.38
    οιν
    -0.38
    kym
    -0.38
    ()")
    -0.38
    POSITIVE LOGITS
    onAttach
    0.78
     useDispatch
    0.73
     BoxFit
    0.70
     Factbook
    0.65
    ValueStyle
    0.64
    SpringRunner
    0.63
     Bowles
    0.63
    ApiModel
    0.63
    DBNull
    0.62
     poussière
    0.62
    Activations Density 1.236%

    No Known Activations