© 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. 5-CLT-HP
    4. 94344
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     Мексичка
    -0.68
     للاسماء
    -0.65
     Theſe
    -0.65
     Efq
    -0.64
     DbType
    -0.61
     XNUMX
    -0.61
    NUMX
    -0.60
     kasarigan
    -0.60
     dzisiaj
    -0.58
     Compl
    -0.57
    POSITIVE LOGITS
     and
    0.63
     &
    0.55
     ".
    0.54
     “
    0.53
    metheus
    0.50
    Errorf
    0.49
     "
    0.48
    astify
    0.48
     over
    0.47
     especially
    0.47
    Activations Density 0.002%

    No Known Activations