© 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. 1270
    Prev
    Next
    INDEX
    Explanations

    code/errors

    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
    ite
    -0.96
    ?
    -0.54
    ¿
    -0.54
    ITE
    -0.53
    ها
    -0.50
    nos
    -0.49
    stine
    -0.48
     plata
    -0.46
    next
    -0.45
    ->
    -0.45
    POSITIVE LOGITS
    ^(@)
    1.09
    wiſe
    1.02
     تضيفلها
    0.96
     itſelf
    0.89
    writeFieldEnd
    0.88
     myſelf
    0.88
    neſs
    0.84
    %]
    0.84
    AndEndTag
    0.83
    — 
    0.82
    Activations Density 1.461%

    No Known Activations