© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38683
    Prev
    Next
    INDEX
    Explanations

    lida

    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
    ی
    -0.83
    ULE
    -0.82
    ing
    -0.80
    ième
    -0.71
    tling
    -0.70
    ING
    -0.69
    ULI
    -0.68
    enance
    -0.67
    ULA
    -0.65
    ه
    -0.65
    POSITIVE LOGITS
    <bos>
    0.81
     Jefus
    0.75
     Phry
    0.71
     Shaksp
    0.69
     Majefty
    0.69
     beſt
    0.68
     fathoms
    0.67
     Shakspeare
    0.67
     eruption
    0.67
     thyself
    0.67
    Activations Density 0.166%

    No Known Activations