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. 30253
    Prev
    Next
    INDEX
    Explanations

    specific structured data formats or numerical values related to system performance

    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
    hü
    -0.44
     Relaciones
    -0.41
     objective
    -0.40
     Ham
    -0.39
    DEST
    -0.39
     anonyme
    -0.39
    ütt
    -0.38
    CONFIGURATION
    -0.36
    Destination
    -0.35
     setName
    -0.35
    POSITIVE LOGITS
    tagHelperRunner
    1.10
     typelib
    1.06
    setVerticalGroup
    1.02
    adaptiveStyles
    1.00
    цездатний
    1.00
     незавершена
    0.99
     defaultstate
    0.99
    IsMutable
    0.97
    OGND
    0.96
    ViewImports
    0.96
    Activations Density 0.000%

    No Known Activations