© 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. 97133
    Prev
    Next
    INDEX
    Explanations

    former

    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
    Lähteet
    -1.03
     الرياضيه
    -0.91
     saites
    -0.91
    MigrationBuilder
    -0.87
     InputDecoration
    -0.84
     kasarigan
    -0.80
    MemoryWarning
    -0.78
     समीक्षाओं
    -0.78
     estekak
    -0.76
     pouvoit
    -0.76
    POSITIVE LOGITS
     type
    0.82
     form
    0.72
     kind
    0.66
     version
    0.61
     and
    0.60
    type
    0.59
     case
    0.58
     sort
    0.56
     example
    0.56
     but
    0.53
    Activations Density 0.086%

    No Known Activations