© 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. 20-CLT-HP
    4. 74816
    Prev
    Next
    INDEX
    Explanations

    Code snippets/excerpts

    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
     surla
    -0.69
    
    -0.63
    FailureListener
    -0.62
     '\\;'
    -0.60
     للاسماء
    -0.58
    ContentAsync
    -0.57
     OMITBAD
    -0.57
     متعلقه
    -0.56
     schéma
    -0.52
    ⓧ
    -0.51
    POSITIVE LOGITS
    denly
    0.51
    $
    
    0.50
    fgaben
    0.48
     suffit
    0.47
    Ỗ
    0.47
     clen
    0.46
    찮
    0.45
    __*/
    0.44
    >`;
    0.44
    (";
    0.44
    Activations Density 0.000%

    No Known Activations