© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4965
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating sentence endings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     виправивши
    -1.27
     typelib
    -1.26
    parsedMessage
    -1.25
    CloseOperation
    -1.23
    AsUp
    -1.15
     disambiguazione
    -1.13
    RenderAtEndOf
    -1.13
    StoryboardSegue
    -1.12
    ViewFeatures
    -1.11
    Personensuche
    -1.09
    POSITIVE LOGITS
    .
    0.64
     V
    0.56
     con
    0.48
     with
    0.48
     I
    0.47
     v
    0.46
    et
    0.46
     .
    0.46
     su
    0.45
    un
    0.45
    Activations Density 0.012%

    No Known Activations