© 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. 11579
    Prev
    Next
    INDEX
    Explanations

    various instances of the word "For" and its variations, indicating multiple references to purpose or intent within the text

    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
    "}")
    -0.75
    >");
    -0.62
    >")
    -0.61
    ly
    -0.59
     beit
    -0.59
    넷
    -0.59
    '>"
    -0.58
    */)
    -0.56
    </b>
    -0.53
    )",
    -0.52
    POSITIVE LOGITS
    ########.
    1.16
    脚注の使い方
    0.99
    Παραπομπές
    0.81
     Hermans
    0.77
    unhofer
    0.77
    byshire
    0.76
    expiresIn
    0.76
    Tại
    0.75
    Kjelder
    0.75
    NOPQRST
    0.75
    Activations Density 0.042%

    No Known Activations