© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26674
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols in structured text, indicating the end of statements or sections

    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
    "):
    -1.29
     endblock
    -1.23
    ']))
    -1.21
    "])
    -1.19
    ")));
    -1.18
    Portale
    -1.14
    MigrationBuilder
    -1.13
    ]){
    -1.12
    SBATCH
    -1.10
    `,
    -1.09
    POSITIVE LOGITS
    ↵
    0.71
    (
    0.69
    es
    0.66
    ce
    0.66
     שב
    0.66
     מה
    0.66
     nici
    0.66
    <blockquote>
    0.65
    last
    0.63
     nej
    0.63
    Activations Density 0.303%

    No Known Activations