© 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. 42380
    Prev
    Next
    INDEX
    Explanations

    Medical procedures

    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
     itſelf
    -1.66
     purpoſe
    -1.65
     myſelf
    -1.63
     pleaſure
    -1.59
     ſeveral
    -1.55
     ſtate
    -1.52
     feroit
    -1.51
     ſche
    -1.50
     Majefty
    -1.49
     Efq
    -1.46
    POSITIVE LOGITS
    s
    1.45
    er
    1.39
    ing
    1.26
    es
    1.09
    ers
    1.07
    ed
    0.93
    ness
    0.91
    ی
    0.91
    y
    0.90
    n
    0.88
    Activations Density 0.161%

    No Known Activations