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. 14758
    Prev
    Next
    INDEX
    Explanations

    the concept of independent or self-sufficient entities or ideas

    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
     kasarigan
    -0.93
    MemoryWarning
    -0.79
     صوتيه
    -0.71
    Tembelea
    -0.68
    icioso
    -0.61
    ISODE
    -0.60
    cosity
    -0.57
     Crusoe
    -0.56
     bs
    -0.56
    ̥
    -0.55
    POSITIVE LOGITS
    WriteLiteral
    0.53
    ?''
    0.52
    鈥
    0.48
     vPvB
    0.46
    ?),
    0.45
    ?")
    0.43
    ethene
    0.42
    ?',
    0.42
     tambi
    0.42
    '?
    0.42
    Activations Density 0.002%

    No Known Activations