© 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. 10464
    Prev
    Next
    INDEX
    Explanations

    stellar

    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
    expandindo
    -0.81
    tagext
    -0.79
    
    -0.77
    +#+#
    -0.73
     disponibilités
    -0.73
     LayoutInflater
    -0.72
    ArgsConstructor
    -0.72
     BorderRadius
    -0.69
    ()]);
    -0.69
    ioutil
    -0.68
    POSITIVE LOGITS
     blij
    0.35
     terang
    0.35
    ždy
    0.34
    ecd
    0.33
    ebus
    0.33
    Glob
    0.32
     araña
    0.30
     सब
    0.29
    REAM
    0.29
     reconocido
    0.29
    Activations Density 0.012%

    No Known Activations