© 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. 3090
    Prev
    Next
    INDEX
    Explanations

    Formal/Academic topics

    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
    Legături
    -0.50
    jface
    -0.50
     actionMode
    -0.49
     Italijanski
    -0.48
     információk
    -0.47
    errHandler
    -0.47
     링크
    -0.47
    ñadir
    -0.46
    >{@
    -0.46
     "
    -0.46
    POSITIVE LOGITS
    CloseOperation
    0.72
    Portale
    0.65
    Autoritní
    0.64
     mourut
    0.63
     Bucharest
    0.56
     noDo
    0.55
    awtextra
    0.53
    %");
    0.53
     parlant
    0.53
    <bos>
    0.52
    Activations Density 0.001%

    No Known Activations