© 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. 530
    Prev
    Next
    INDEX
    Explanations

    dialogue and quotations

    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
    Autoritní
    -0.78
    StructEnd
    -0.74
    aarrggbb
    -0.73
    alnız
    -0.68
     faſt
    -0.66
     myſelf
    -0.65
    AndEndTag
    -0.63
     purpoſe
    -0.63
     ſte
    -0.60
    sedi
    -0.58
    POSITIVE LOGITS
     kaynağından
    0.69
     MainAxisSize
    0.63
    ModelBuilder
    0.62
    Yeah
    0.58
    Mmm
    0.57
    Бахар
    0.56
    addPreferredGap
    0.55
    readObject
    0.54
    SuppressLint
    0.54
    BeginInit
    0.53
    Activations Density 0.112%

    No Known Activations