Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 22185
    Prev
    Next
    INDEX
    Explanations

    factors related to numerical values or quantitative concepts

    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
    RenderAtEndOf
    -0.66
    WithIOException
    -0.65
    FormTagHelper
    -0.49
    السكان
    -0.48
    colorbar
    -0.48
     either
    -0.47
    мум
    -0.47
     հղումներ
    -0.46
    besch
    -0.45
    ÉN
    -0.45
    POSITIVE LOGITS
    __':
    
    0.67
     Romains
    0.65
    batore
    0.63
    __*/
    0.61
     Jalisco
    0.61
    tonsoft
    0.60
    〢
    0.60
    ViewImports
    0.59
    inburgh
    0.58
    inspace
    0.57
    Activations Density 0.012%

    No Known Activations