© 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. 42754
    Prev
    Next
    INDEX
    Explanations

    lipids

    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
    ed
    -0.98
    es
    -0.91
    s
    -0.89
    e
    -0.78
    er
    -0.73
    em
    -0.64
    et
    -0.61
    ه
    -0.61
    eu
    -0.61
    ia
    -0.59
    POSITIVE LOGITS
    IDENTAL
    0.75
    complexType
    0.67
    principalColumn
    0.61
    naments
    0.60
    ugal
    0.59
     Мексичка
    0.57
     @"/
    0.57
     calendriers
    0.57
    creep
    0.56
    glades
    0.56
    Activations Density 0.066%

    No Known Activations