© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 3-RES-MATRYOSHKA-DC
    4. 156
    Prev
    Next
    INDEX
    Explanations

    code snippets with '$' operator.

    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
     defaultstate
    -1.09
     estekak
    -0.93
    SequentialGroup
    -0.91
    \}\\
    -0.89
     للاسماء
    -0.89
     '\\;'
    -0.85
    তথ্যসূত্র
    -0.85
    StoryboardSegue
    -0.84
    ")))
    -0.82
     الرياضيه
    -0.82
    POSITIVE LOGITS
     $
    1.49
    $
    1.47
     \$
    1.32
     $\$
    1.20
    ($
    1.19
    \$
    1.19
    ="<?=$
    1.09
    /$
    1.07
    ://$
    1.06
    //$
    1.05
    Activations Density 0.832%

    No Known Activations