© 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. 707
    Prev
    Next
    INDEX
    Explanations

    section ends and numbers, likely for citations, begin

    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
     Efq
    -0.79
     itſelf
    -0.79
    يكب
    -0.77
    ſelf
    -0.74
    Panamoan
    -0.71
     whoſe
    -0.71
     beginnetje
    -0.71
     myſelf
    -0.69
     Houſe
    -0.69
     purpoſe
    -0.67
    POSITIVE LOGITS
    <h3>
    0.83
    <h2>
    0.77
    <h4>
    0.68
    <strong>
    0.66
     next
    0.65
     Lastly
    0.63
     Thirdly
    0.62
     Finally
    0.61
    Finally
    0.61
     finally
    0.60
    Activations Density 1.815%

    No Known Activations