© 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. 12-RES-MATRYOSHKA-DC
    7. 18527
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special symbols

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    ftagPool
    -1.16
     ―――――
    -1.13
    AndEndTag
    -1.04
     Réponses
    -1.00
     utafitiHapana
    -1.00
    Билгалдахарш
    -0.98
    awtextra
    -0.97
     photolibrary
    -0.96
     doubtnut
    -0.96
    Autoritní
    -0.94
    POSITIVE LOGITS
    ↵↵
    0.67
    <eos>
    0.66
     F
    0.53
     wa
    0.52
    inn
    0.52
     G
    0.50
     Ba
    0.50
     N
    0.50
     am
    0.49
    zulegen
    0.49
    Activations Density 0.006%

    No Known Activations