© 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. 1-CLT-HP
    7. 14673
    Prev
    Next
    INDEX
    Explanations

    mechanics and feedback systems

    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
     '\\;'
    -0.69
    Autoritní
    -0.60
    Normdaten
    -0.55
    Obrázky
    -0.54
    localctx
    -0.53
     tattooed
    -0.52
     leprosy
    -0.50
    Espèce
    -0.49
     ListTile
    -0.49
    Formik
    -0.48
    POSITIVE LOGITS
     box
    0.56
     Box
    0.56
     BOX
    0.51
    Box
    0.51
    IntoConstraints
    0.48
    цездатний
    0.47
    uttavia
    0.47
     Ta
    0.47
     Late
    0.47
    setSubject
    0.47
    Activations Density 0.034%

    No Known Activations