© 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. 28667
    Prev
    Next
    INDEX
    Explanations

    numerical data and values, possibly related to statistics or measurements

    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
     estimés
    -0.89
    afficheront
    -0.83
    ContentAsync
    -0.72
    endpush
    -0.71
    StructEnd
    -0.69
    脚注の使い方
    -0.69
     ISNI
    -0.68
    Tikang
    -0.67
    GEBURTSDATUM
    -0.67
    protoimpl
    -0.64
    POSITIVE LOGITS
    HasForeignKey
    0.56
    OneToMany
    0.45
    ToScroll
    0.43
    nea
    0.42
    canny
    0.41
    audiovisuel
    0.41
     следующем
    0.41
    níků
    0.41
    pertise
    0.40
     total
    0.40
    Activations Density 0.018%

    No Known Activations