© 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. 24448
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences or identifiers typically found in URLs or code snippets

    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
    findpost
    -0.84
    sidemargin
    -0.82
    ########.
    -0.72
     pleaſure
    -0.72
    ADELPHIA
    -0.69
    /*
    -0.68
     purpoſe
    -0.68
    apimachinery
    -0.66
    tagHelperRunner
    -0.66
    nezeu
    -0.66
    POSITIVE LOGITS
    LookAnd
    0.50
     put
    0.46
     tanggung
    0.45
    unknownFields
    0.44
    badlogic
    0.44
    PasswordEncoder
    0.42
     uns
    0.42
    withIdentifier
    0.41
     EdgeInsets
    0.41
    reportWebVitals
    0.40
    Activations Density 0.003%

    No Known Activations