© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38372
    Prev
    Next
    INDEX
    Explanations

    Introduces example/transition

    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
     Namely
    -1.04
     Theſe
    -0.92
     ProtoMessage
    -0.88
     betweenstory
    -0.85
     onCancelled
    -0.82
    parsedMessage
    -0.81
     beginnetje
    -0.80
     виправивши
    -0.77
    AccessorTable
    -0.76
    tvguidetime
    -0.76
    POSITIVE LOGITS
     though
    0.61
    ,
    0.61
     to
    0.59
     yet
    0.58
     able
    0.56
     with
    0.54
     like
    0.51
     operated
    0.51
     about
    0.50
     speaking
    0.49
    Activations Density 0.060%

    No Known Activations