© 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. 16408
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly semicolons and periods

    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
    ონ
    -0.41
     vermelhas
    -0.40
    pData
    -0.39
    getKeyCode
    -0.39
    tinta
    -0.38
    HUB
    -0.37
    DERE
    -0.37
    BURGH
    -0.36
    Sprintf
    -0.36
    née
    -0.36
    POSITIVE LOGITS
     متعلقه
    1.25
    SharedCtor
    0.96
     resourceCulture
    0.89
    Tembelea
    0.88
    WriteTagHelper
    0.88
    fromnode
    0.87
    SourceChecksum
    0.87
     архивлан
    0.86
    providedIn
    0.85
     MainAxisSize
    0.84
    Activations Density 0.001%

    No Known Activations