© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41592
    Prev
    Next
    INDEX
    Explanations

    html tags

    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
    存于互联网档案馆
    -0.75
    sizeCache
    -0.71
    endphp
    -0.70
    Smarty
    -0.68
    arusian
    -0.68
    Jeografia
    -0.68
    StructEnd
    -0.67
    useum
    -0.65
     unknownFields
    -0.64
     OMITBAD
    -0.63
    POSITIVE LOGITS
     golos
    0.51
     intermedi
    0.49
    BeginContext
    0.48
    ed
    0.47
    ={({
    0.45
     beginning
    0.44
     Dunbar
    0.44
     lots
    0.43
     subordin
    0.43
     futbol
    0.42
    Activations Density 0.113%

    No Known Activations