© 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. 14797
    Prev
    Next
    INDEX
    Explanations

    references to previous studies or findings

    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
    awtextra
    -0.82
    httphttps
    -0.80
    SourceChecksum
    -0.76
    脚注の使い方
    -0.74
     Exacts
    -0.73
    __":
    -0.72
     kaarangay
    -0.71
    COUVER
    -0.71
    Hentet
    -0.68
    Geplaatst
    -0.68
    POSITIVE LOGITS
     or
    0.47
     is
    0.46
     personal
    0.43
    useEffect
    0.41
    ேர
    0.39
     family
    0.39
    GeneratedValue
    0.39
     vendre
    0.39
     that
    0.39
    面目
    0.39
    Activations Density 0.015%

    No Known Activations