© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16081
    Prev
    Next
    INDEX
    Explanations

    periods and numerical values related to software versioning

    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
    tagHelperRunner
    -0.79
    AutoScale
    -0.67
    providedIn
    -0.65
    сылкі
    -0.65
    reportWebVitals
    -0.64
    hbs
    -0.60
    oa̍t
    -0.60
    djangoproject
    -0.59
    OGND
    -0.59
     дописавши
    -0.57
    POSITIVE LOGITS
     joaat
    0.61
     onPostExecute
    0.61
    ranslated
    0.58
    prepareStatement
    0.55
     auprès
    0.54
     löytyy
    0.54
     strtok
    0.52
    XMLSchema
    0.52
    bia
    0.52
     Pologne
    0.52
    Activations Density 0.004%

    No Known Activations