© 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. 2774
    Prev
    Next
    INDEX
    Explanations

    unusual or unconventional formatting and presentation 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
    KommentareTeilen
    -0.60
    ressee
    -0.59
    VersionUID
    -0.59
    BackStack
    -0.55
    ]='\
    -0.55
    sard
    -0.55
    ngdoc
    -0.54
    gasus
    -0.54
    ChildIndex
    -0.54
    
    -0.54
    POSITIVE LOGITS
    bootstrapcdn
    0.71
    "]));
    0.60
    ContentAsync
    0.60
     braccia
    0.60
     chré
    0.59
    hoeddwyd
    0.59
    .}}
    0.59
    IsMutable
    0.58
    SequentialGroup
    0.57
    transQ
    0.57
    Activations Density 0.419%

    No Known Activations