© 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. 42527
    Prev
    Next
    INDEX
    Explanations

    anatomy

    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
     chemistry
    -1.18
     anatomy
    -1.14
     houſe
    -1.09
     myſelf
    -1.09
     Anatomy
    -1.04
     reaſon
    -1.04
     Efq
    -1.04
     HasFactory
    -1.03
     ſtate
    -1.02
     ſever
    -1.02
    POSITIVE LOGITS
    s
    0.62
    ic
    0.59
    d
    0.58
    .
    0.55
    se
    0.54
    ns
    0.54
    nya
    0.54
     v
    0.53
     (
    0.53
    ly
    0.53
    Activations Density 0.124%

    No Known Activations