© 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. 9854
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names associated with influential figures or organizations

    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
    ⓧ
    -0.87
     incomplète
    -0.66
    XmlAccessType
    -0.66
     tartalomajánló
    -0.62
    AndEndTag
    -0.60
    期刊论文
    -0.59
     дописавши
    -0.59
    SharedDtor
    -0.56
    COUVER
    -0.55
    MigrationBuilder
    -0.54
    POSITIVE LOGITS
     estimés
    0.47
    grà
    0.47
     samples
    0.45
    libft
    0.45
    dut
    0.45
    land
    0.44
     Samples
    0.44
    всем
    0.44
     policies
    0.43
     felices
    0.43
    Activations Density 0.364%

    No Known Activations