© 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. 43017
    Prev
    Next
    INDEX
    Explanations

    visit

    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
    GraphicsUnit
    -0.63
     noastre
    -0.63
     חיצוניים
    -0.61
     purpoſe
    -0.58
     automatico
    -0.54
     pleaſure
    -0.54
    GenerationType
    -0.54
     noastră
    -0.53
     legales
    -0.51
     nargin
    -0.50
    POSITIVE LOGITS
     to
    0.79
    ://"
    0.57
     be
    0.56
    *}{
    0.54
    Msp
    0.54
     Por
    0.54
    atii
    0.54
    дати
    0.53
    nte
    0.52
    dsi
    0.52
    Activations Density 0.036%

    No Known Activations