© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4205
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to algorithms and mathematical frameworks in data analysis

    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
     pleaſure
    -0.81
    CodeAttribute
    -0.78
     Eſ
    -0.77
     Reſ
    -0.75
    IndentedString
    -0.70
     ویکی‌پدیا
    -0.70
     Verſ
    -0.67
     ſche
    -0.66
     houſe
    -0.66
     purpoſe
    -0.65
    POSITIVE LOGITS
    endpush
    0.54
    :✨
    0.50
    +#+#
    0.49
    Legături
    0.49
     tartalomajánló
    0.48
    plaatsen
    0.48
     Em
    0.47
     коли
    0.47
    chyma
    0.46
    __((
    0.46
    Activations Density 1.022%

    No Known Activations