© 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. 1493
    Prev
    Next
    INDEX
    Explanations

    unparalleled

    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
     INTERESAR
    -0.74
    endregion
    -0.72
    InjectAttribute
    -0.68
    aarrggbb
    -0.68
    UpInside
    -0.65
    djangoproject
    -0.65
    GEBURTSDATUM
    -0.64
     bicchiere
    -0.64
     unsurpassed
    -0.64
     indistingu
    -0.63
    POSITIVE LOGITS
    ly
    0.62
    ize
    0.59
    ็จ
    0.54
     private
    0.54
    ient
    0.54
    ized
    0.52
    퀀
    0.51
     quantities
    0.50
     word
    0.47
    ificantly
    0.47
    Activations Density 0.047%

    No Known Activations