© 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. 32235
    Prev
    Next
    INDEX
    Explanations

    references to height measurements

    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
    openConnection
    -0.67
    endregion
    -0.60
    EndContext
    -0.60
     nahilalakip
    -0.60
    FOOTNOTES
    -0.59
     okuyayım
    -0.57
    .'-
    -0.55
    Revenir
    -0.53
     Easier
    -0.52
    Filmografie
    -0.52
    POSITIVE LOGITS
     SALT
    0.76
     Knowles
    0.75
     distance
    0.65
     démocr
    0.65
    ftant
    0.64
    UpdateCommand
    0.62
     Kie
    0.61
     entanto
    0.61
     voter
    0.60
    yadh
    0.60
    Activations Density 0.004%

    No Known Activations