© 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. 18-RES-MATRYOSHKA-DC
    7. 55
    Prev
    Next
    INDEX
    Explanations

    proper names of people, places, organizations, and creative works

    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.18.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.18.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
    )++;
    -0.80
    setVerticalGroup
    -0.79
    $")
    -0.77
     مشين
    -0.75
     بيها
    -0.75
    InputBorder
    -0.71
    +#+#
    -0.71
    liament
    -0.69
    ReusableCell
    -0.68
     autorytatywna
    -0.68
    POSITIVE LOGITS
     Jr
    0.68
     himself
    0.61
    '
    0.61
    ’
    0.61
     ſaid
    0.59
     himſelf
    0.56
     wrote
    0.50
     ίδ
    0.50
     ſhould
    0.49
    Jr
    0.49
    Activations Density 5.241%

    No Known Activations