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. 10192
    Prev
    Next
    INDEX
    Explanations

    references to copyright and rights management

    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
     Reserved
    -1.02
     reserved
    -1.01
     RESERVED
    -0.79
    reserved
    -0.72
     reserving
    -0.71
    Reserved
    -0.70
     reservado
    -0.68
    GeneratedValue
    -0.66
    duled
    -0.66
    esteld
    -0.65
    POSITIVE LOGITS
     تضيفلها
    0.67
    ratos
    0.57
    DebuggerStep
    0.57
    ]{\
    0.57
     Rights
    0.56
    `).
    0.54
    tritte
    0.52
    PageRoute
    0.52
    InsertCommand
    0.52
     rights
    0.51
    Activations Density 0.001%

    No Known Activations