© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92992
    Prev
    Next
    INDEX
    Explanations

    Bea, fetus

    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
    各样的
    -0.54
    al
    -0.52
     Bea
    -0.51
    Al
    -0.49
     
    -0.49
    el
    -0.49
     fo
    -0.47
    inus
    -0.47
    cus
    -0.46
     Science
    -0.45
    POSITIVE LOGITS
    Personensuche
    0.85
     ་་
    0.84
     ſind
    0.81
     lordship
    0.77
     itſelf
    0.77
     Shakspeare
    0.75
     Efq
    0.73
     ―――――
    0.73
     Mauri
    0.70
     homotopy
    0.69
    Activations Density 1.978%

    No Known Activations