© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42204
    Prev
    Next
    INDEX
    Explanations

    scientific publications

    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
     II
    -0.83
    ii
    -0.82
    Datuak
    -0.80
    II
    -0.77
     Ii
    -0.77
     stället
    -0.76
     ii
    -0.73
    bbene
    -0.73
     skolan
    -0.72
    ########.
    -0.71
    POSITIVE LOGITS
     bas
    0.58
     nakalista
    0.57
     of
    0.54
    참고
    0.51
    例句
    0.51
     av
    0.50
    ViewChild
    0.50
     pu
    0.48
    BaseAdapter
    0.47
     am
    0.45
    Activations Density 0.042%

    No Known Activations