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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 154
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to observations

    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
     Threatened
    -0.42
    eder
    -0.41
     Circuit
    -0.41
    Chance
    -0.40
    is
    -0.40
     chân
    -0.40
    Profession
    -0.40
    Resources
    -0.39
     Profession
    -0.39
     Threat
    -0.39
    POSITIVE LOGITS
    にかけて
    0.89
    NUMX
    0.75
     InputDecoration
    0.73
     समीक्षाओं
    0.72
     Theſe
    0.71
    oredCriteria
    0.71
    depending
    0.70
     depending
    0.70
    WithIOException
    0.70
     között
    0.69
    Activations Density 1.748%

    No Known Activations