© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24417
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "length" in code-related contexts

    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
    Negative Logits
    MigrationBuilder
    -0.94
    ExtendWith
    -0.91
    AntiForgeryToken
    -0.81
    mergeFrom
    -0.81
    رشف
    -0.79
     Nacionales
    -0.79
     saites
    -0.79
    terness
    -0.78
     חיצוניים
    -0.78
     OMITBAD
    -0.78
    POSITIVE LOGITS
    .
    0.65
     work
    0.53
    ,
    0.51
    相
    0.48
    <sup>
    0.48
    ErrorResponse
    0.47
     once
    0.47
    y
    0.46
    randrange
    0.46
    package
    0.46
    Activations Density 0.002%

    No Known Activations