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. 25044
    Prev
    Next
    INDEX
    Explanations

    references to themes of observation and metaphorical relationships

    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
    IZA
    -0.52
    েই
    -0.52
    шой
    -0.48
    raphe
    -0.48
    asche
    -0.48
     пови
    -0.47
    idiary
    -0.46
    GBT
    -0.46
    ített
    -0.46
    ゚)
    -0.46
    POSITIVE LOGITS
    sizeCache
    0.68
     للاسماء
    0.68
     الحره
    0.66
     صوتيه
    0.65
    rrggbb
    0.64
     ujednoznacz
    0.62
    Personensuche
    0.60
    ttemberg
    0.59
    stateProvider
    0.59
     analogy
    0.59
    Activations Density 0.041%

    No Known Activations