© 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. 5-CLT-HP
    7. 98051
    Prev
    Next
    INDEX
    Explanations

    that

    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
     that
    -0.77
     who
    -0.66
     whose
    -0.65
    Whose
    -0.58
     which
    -0.56
     cuya
    -0.56
    whose
    -0.55
     mergeFrom
    -0.55
    sizeCache
    -0.53
     cuyo
    -0.52
    POSITIVE LOGITS
     насељу
    0.66
    kunde
    0.56
    expandindo
    0.55
     piedi
    0.55
    :+:
    0.54
     affitto
    0.54
    arschijnlijk
    0.54
     sportivo
    0.53
    klein
    0.52
    ownic
    0.52
    Activations Density 0.001%

    No Known Activations