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. 8714
    Prev
    Next
    INDEX
    Explanations

    sections or delimiters that indicate the structure of a document or report

    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
     skog
    -0.69
     Roper
    -0.67
    onNext
    -0.65
    Volker
    -0.64
    ppet
    -0.61
     Foster
    -0.60
    afar
    -0.60
    URO
    -0.59
     FormGroup
    -0.59
     Hogar
    -0.59
    POSITIVE LOGITS
    ==========
    1.07
    AddTagHelper
    1.02
     contextLoads
    0.89
    例句
    0.75
     Walkover
    0.73
     newState
    0.72
    dafx
    0.71
    Personensuche
    0.71
    Aktualisiert
    0.71
    sack
    0.70
    Activations Density 0.003%

    No Known Activations