© 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. 95045
    Prev
    Next
    INDEX
    Explanations

    GPUs

    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
    حياته
    -0.64
    höhe
    -0.61
    حياتها
    -0.59
    romyal
    -0.59
    ilight
    -0.59
    encils
    -0.56
    WebServlet
    -0.56
    milla
    -0.55
     Satellite
    -0.54
     vux
    -0.54
    POSITIVE LOGITS
    ary
    0.76
    ous
    0.59
    al
    0.57
    ative
    0.55
    an
    0.54
    age
    0.54
    o
    0.54
    ation
    0.54
    MLLoader
    0.51
    ant
    0.49
    Activations Density 0.080%

    No Known Activations