© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1681
    Prev
    Next
    INDEX
    Explanations

    math equations (often with many numbers)

    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
    ionine
    -0.49
    itettura
    -0.49
     segni
    -0.48
    GEBURTSDATUM
    -0.48
     Tug
    -0.45
    kurat
    -0.45
    trunk
    -0.44
    redux
    -0.44
     pass
    -0.44
    dingen
    -0.44
    POSITIVE LOGITS
    )/
    1.02
    "]/
    0.93
    }/
    0.93
    ]/
    0.91
    )/(
    0.85
    "/
    0.84
    }*
    0.78
     ویکی‌پدیا
    0.76
    ########.
    0.76
    ']/
    0.76
    Activations Density 0.727%

    No Known Activations