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. 25533
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating degrees of prominence or significance

    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
     extensively
    -0.56
    Controllo
    -0.56
     nakalista
    -0.54
    :].
    -0.53
     wireType
    -0.53
    σιμοποι
    -0.53
     quæ
    -0.52
    stylers
    -0.50
     both
    -0.49
    ')")
    -0.49
    POSITIVE LOGITS
     estekak
    0.63
     contextLoads
    0.59
    SpringBootTest
    0.56
     AssemblyCompany
    0.55
    antMatchers
    0.55
    슷
    0.54
    pośred
    0.53
    RRect
    0.52
    TargetException
    0.52
     menengah
    0.52
    Activations Density 0.068%

    No Known Activations