© 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. 95253
    Prev
    Next
    INDEX
    Explanations

    eye

    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
     eye
    -0.90
     يتيمه
    -0.87
    Personendaten
    -0.86
    Tembelea
    -0.84
    ConstraintMaker
    -0.83
     épaules
    -0.82
     مرئيه
    -0.81
     genoux
    -0.77
     NgModule
    -0.75
    脚注の使い方
    -0.75
    POSITIVE LOGITS
     to
    0.45
    glass
    0.42
     structures
    0.42
     products
    0.41
     pen
    0.41
     produced
    0.40
    batore
    0.38
     regional
    0.38
    身を
    0.37
     nią
    0.36
    Activations Density 0.018%

    No Known Activations