© 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. 5443
    Prev
    Next
    INDEX
    Explanations

    components that indicate measurements of performance or quality in various contexts

    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
    JsonInclude
    -0.54
     thủ
    -0.49
    OVERALL
    -0.47
    iecie
    -0.45
     letter
    -0.45
    Abit
    -0.45
    OPHER
    -0.44
    atimes
    -0.44
    bzero
    -0.43
     leksikon
    -0.43
    POSITIVE LOGITS
    ]")]
    0.85
    httphttps
    0.64
    сылкі
    0.60
    tagHelperRunner
    0.60
    PerformLayout
    0.59
     ostavi
    0.57
     useParams
    0.56
     '\\;'
    0.56
     (~
    0.56
    enumii
    0.56
    Activations Density 0.897%

    No Known Activations