© 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. 20-CLT-HP
    7. 75786
    Prev
    Next
    INDEX
    Explanations

    network

    np_max-act-logits · 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
    expandindo
    -0.69
    IVEREF
    -0.60
     autorytatywna
    -0.60
    PullParser
    -0.59
    lossians
    -0.57
    riwal
    -0.57
     betweenstory
    -0.56
    AndEndTag
    -0.56
    yntaxException
    -0.55
     ProtoMessage
    -0.54
    POSITIVE LOGITS
    attached
    0.68
     attached
    0.63
    jenner
    0.63
    Gambas
    0.60
     Attached
    0.60
     szám
    0.55
    booted
    0.54
     morgon
    0.51
    edale
    0.51
    nyttet
    0.50
    Activations Density 0.003%

    No Known Activations