© 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. 26580
    Prev
    Next
    INDEX
    Explanations

    references to the National Register of Historic Places

    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
    getSystemService
    -0.50
    όμε
    -0.47
    Sprites
    -0.45
    setCellValue
    -0.45
     الحره
    -0.45
     celebración
    -0.45
     Thurman
    -0.44
    vatar
    -0.43
     articol
    -0.43
    wakilan
    -0.43
    POSITIVE LOGITS
     estekak
    0.95
    таратура
    0.93
    setVerticalGroup
    0.89
     مرئيه
    0.84
     صوتيه
    0.80
     betweenstory
    0.78
     Anſ
    0.77
    BeginContext
    0.77
     ―――――
    0.76
     Majefty
    0.76
    Activations Density 0.001%

    No Known Activations