© 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. 12-RES-MATRYOSHKA-DC
    7. 20151
    Prev
    Next
    INDEX
    Explanations

    structural components of clauses and phrases in text

    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
    Бахар
    -0.73
    writeFieldEnd
    -0.73
     typelib
    -0.72
    IVEREF
    -0.69
     externi
    -0.68
     onPostExecute
    -0.65
    MemoryWarning
    -0.64
    FundMe
    -0.63
    NewUrlParser
    -0.62
     snippetHide
    -0.62
    POSITIVE LOGITS
    bitField
    0.60
    Read
    0.48
    First
    0.47
     First
    0.46
    gatsby
    0.45
     Wing
    0.45
    ppelin
    0.45
     Daß
    0.45
     Gla
    0.44
    Free
    0.44
    Activations Density 0.017%

    No Known Activations