© 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. 15669
    Prev
    Next
    INDEX
    Explanations

    art descriptions

    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
    art
    -0.65
     paint
    -0.63
     painting
    -0.62
    s
    -0.60
    .
    -0.59
    f
    -0.59
     art
    -0.58
    ,
    -0.57
    a
    -0.57
    ↵↵
    -0.57
    POSITIVE LOGITS
    tagHelperRunner
    1.18
    IntoConstraints
    1.05
    __":
    1.05
     }}"></
    0.99
    NUMX
    0.98
     autorytatywna
    0.96
    __':
    0.96
     Audiodateien
    0.96
    "):
    0.95
     MyBatis
    0.94
    Activations Density 0.015%

    No Known Activations