© 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. 22-RES-MATRYOSHKA-DC
    7. 186
    Prev
    Next
    INDEX
    Explanations

    phone numbers, URLs, or possibly other sequences of numbers or letters

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    WithMany
    -0.81
    Примечания
    -0.71
    extAlignment
    -0.68
     مواليد
    -0.68
    ceğim
    -0.62
    CppMethod
    -0.60
     kaynağından
    -0.60
    Билгалдахарш
    -0.58
    globalData
    -0.57
    __((
    -0.57
    POSITIVE LOGITS
    8
    0.58
    7
    0.58
    6
    0.57
    9
    0.57
    0
    0.55
    5
    0.54
    3
    0.54
     spesies
    0.54
    4
    0.54
    buie
    0.52
    Activations Density 4.688%

    No Known Activations