© 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
    2. Gemma-2-2B
    3. 3-RES-MATRYOSHKA-DC
    4. 783
    Prev
    Next
    INDEX
    Explanations

    lines that start with comment-related formatting like asterisks or percent signs

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    1
    -0.65
    .
    -0.59
    2
    -0.59
    8
    -0.57
    ↵
    -0.56
    (
    -0.55
    3
    -0.54
    6
    -0.54
    -
    -0.52
    raz
    -0.51
    POSITIVE LOGITS
    -------
    1.16
    WriteBarrier
    1.06
     nahilalakip
    1.05
     Савезне
    1.05
    }))
    
    1.01
    </caption>
    1.00
    ^(@)
    0.99
     */
    
    
    0.99
    */;
    0.98
    dafx
    0.98
    Activations Density 0.513%

    No Known Activations