© 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
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 433
    Prev
    Next
    INDEX
    Explanations

    commas within structured data like code or numerical lists

    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/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    -0.57
    -
    -0.52
    ,
    -0.49
    .
    -0.49
    -0.48
     lenker
    -0.47
    сть
    -0.46
    ’
    -0.45
    ?
    -0.45
     (
    -0.43
    POSITIVE LOGITS
    ,,,,
    1.11
     ...,
    1.11
     etc
    1.10
    ,-,
    1.07
    [],
    1.06
    ,,,
    1.03
    .,,
    1.03
    **,
    0.99
    €,
    0.99
    ~,
    0.98
    Activations Density 3.200%
    No Known Activations