© 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. 94882
    Prev
    Next
    INDEX
    Explanations

    body

    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
     body
    -2.08
    body
    -1.58
    Body
    -1.54
     Body
    -1.53
     BODY
    -1.38
    BODY
    -1.14
     bodies
    -1.07
     cuerpo
    -1.02
    ボディ
    -0.90
     Bodies
    -0.89
    POSITIVE LOGITS
     ProtoMessage
    0.76
     bağlantılar
    0.66
    PerformLayout
    0.65
     endings
    0.65
     surfers
    0.63
    houettes
    0.63
    rzez
    0.63
     silhouettes
    0.62
     ddelweddau
    0.62
     Signalez
    0.61
    Activations Density 0.120%

    No Known Activations