© 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. 1774
    Prev
    Next
    INDEX
    Explanations

    phrases frequently used in scientific papers to describe methods, especially highlighting steps taken and conditions.

    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
     mukaan
    -0.49
     bì
    -0.47
    getOriginal
    -0.46
     tissus
    -0.45
     mellett
    -0.44
     mastered
    -0.43
     loạn
    -0.43
    mą
    -0.43
    urlencoded
    -0.43
     démission
    -0.43
    POSITIVE LOGITS
     تضيفلها
    0.88
     الحره
    0.79
    LookAnd
    0.73
     Allowed
    0.71
    bewerken
    0.71
    subject
    0.70
     שוליים
    0.70
    homonymie
    0.70
     Wiktionnaire
    0.69
     EconPapers
    0.69
    Activations Density 0.454%

    No Known Activations