© 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. 10945
    Prev
    Next
    INDEX
    Explanations

    file types and formats, especially related to configuration and project structuring

    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
     thighs
    -0.47
    idia
    -0.46
    utrition
    -0.45
     instructed
    -0.45
     nors
    -0.45
    ား
    -0.44
     furl
    -0.44
     guaranteeing
    -0.44
     instructions
    -0.44
    ssus
    -0.43
    POSITIVE LOGITS
    windowFixed
    0.84
    Демографія
    0.82
    djangoproject
    0.76
     getItemCount
    0.71
    MessageTagHelper
    0.69
     defaultstate
    0.68
     kasarigan
    0.66
    قایناق‌لار
    0.65
    EndContext
    0.65
    例句
    0.64
    Activations Density 0.023%

    No Known Activations