© 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. 1-CLT-HP
    4. 46029
    Prev
    Next
    INDEX
    Explanations

    technical/research text

    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
     perm
    -0.88
     Perm
    -0.66
    Perm
    -0.57
    contentLoaded
    -0.54
    oredCriteria
    -0.50
    msgSender
    -0.49
    Portály
    -0.48
    parsedMessage
    -0.47
    GeneratedMessage
    -0.45
    ละ
    -0.43
    POSITIVE LOGITS
     Himo
    0.65
    Tikang
    0.59
    ypep
    0.59
     lenker
    0.58
    ianus
    0.56
    غات
    0.54
     sidor
    0.53
    approche
    0.51
    pedes
    0.50
     geográfica
    0.49
    Activations Density 0.006%

    No Known Activations