© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5544
    Prev
    Next
    INDEX
    Explanations

    characters or sequences indicative of numerical representations or structures

    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
    ense
    -0.50
     Krause
    -0.50
    ENSE
    -0.48
    дие
    -0.48
    ****/
    -0.48
    ASSE
    -0.48
     visitor
    -0.47
     corso
    -0.47
    닷
    -0.47
    ENS
    -0.46
    POSITIVE LOGITS
    styleType
    0.77
    ConstraintMaker
    0.77
     سكانية
    0.77
     pinulongan
    0.76
    сылкі
    0.73
    ⓧ
    0.71
    ftagPool
    0.69
     sumpay
    0.67
     saites
    0.67
     समीक्षाएं
    0.66
    Activations Density 0.015%

    No Known Activations