© 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. 19322
    Prev
    Next
    INDEX
    Explanations

    financial impacts and adjustments related to projects and funding scenarios

    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
     voorbij
    -0.53
     pareti
    -0.48
     @{
    -0.43
    헌
    -0.43
     naviguant
    -0.42
     prossima
    -0.42
     īpa
    -0.41
     bientôt
    -0.40
     značky
    -0.40
     patterned
    -0.40
    POSITIVE LOGITS
     lenker
    0.78
     nakalista
    0.72
     postponement
    0.71
    iempo
    0.70
     unexpectedly
    0.69
     kaynağından
    0.67
     resourceCulture
    0.66
    DockStyle
    0.66
     NSCoder
    0.66
     unplanned
    0.65
    Activations Density 0.192%

    No Known Activations