© 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. 42563
    Prev
    Next
    INDEX
    Explanations

    medicine

    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
    ]--;
    -0.93
    ]++;
    -0.74
    cale
    -0.69
     wikipagina
    -0.65
     Hester
    -0.63
    findpost
    -0.63
    mias
    -0.61
     épaules
    -0.60
    apatalk
    -0.59
     oreilles
    -0.57
    POSITIVE LOGITS
    ed
    0.71
    y
    0.67
    er
    0.65
    e
    0.58
    i
    0.54
     Fá
    0.50
    s
    0.49
    yntaxException
    0.49
     GenerationType
    0.48
    ForRow
    0.47
    Activations Density 0.129%

    No Known Activations