© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 94352
    Prev
    Next
    INDEX
    Explanations

    0

    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
     MainAxisSize
    -0.72
     chrétiens
    -0.71
     acrylique
    -0.71
     fidèles
    -0.69
    FundMe
    -0.68
     voisins
    -0.68
     őket
    -0.67
     traditionnels
    -0.66
     Grecs
    -0.66
     médec
    -0.65
    POSITIVE LOGITS
    1
    0.74
    %)
    0.67
    2
    0.62
    '),
    0.58
    %),
    0.58
    ')
    0.57
    %
    0.55
    ?)
    0.54
    ?')
    0.54
    0
    0.54
    Activations Density 0.172%

    No Known Activations