© 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. 4-CLT-HP
    7. 2024
    Prev
    Next
    INDEX
    Explanations

    because

    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
     stöd
    -0.63
    commutative
    -0.59
    presto
    -0.57
    Tôi
    -0.56
    inerary
    -0.56
     détru
    -0.54
    itamos
    -0.54
    encodeWith
    -0.53
    Diwedd
    -0.53
     Infórmanos
    -0.53
    POSITIVE LOGITS
    setVerticalGroup
    0.75
     they
    0.73
     anyone
    0.54
     everyone
    0.52
     anybody
    0.52
    (),"
    0.50
     theyre
    0.48
     theres
    0.48
     luckily
    0.46
    jgl
    0.46
    Activations Density 0.005%

    No Known Activations