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. 25049
    Prev
    Next
    INDEX
    Explanations

    elements of code or markup related to project properties and paths in a configuration file

    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
     тру
    -0.59
    AnimationsModule
    -0.59
     OMITBAD
    -0.54
    KURZBESCHREIBUNG
    -0.52
     Ferner
    -0.51
     ویکی‌پدی
    -0.51
     BIBSYS
    -0.51
     himo
    -0.49
    تقاوى
    -0.49
    añ
    -0.49
    POSITIVE LOGITS
    PropertyGroup
    1.05
     المعيارى
    0.61
     myſelf
    0.60
    AsUp
    0.60
    setVerticalGroup
    0.59
    extAlignment
    0.59
     répondu
    0.58
    sphase
    0.58
     Inseln
    0.57
     بيها
    0.56
    Activations Density 0.004%

    No Known Activations