© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10849
    Prev
    Next
    INDEX
    Explanations

    keywords or phrases indicating legal judgments

    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
    NewUrlParser
    -0.48
    IBarButtonItem
    -0.48
     înal
    -0.48
     LEYENDO
    -0.47
     Mojo
    -0.46
    dailymail
    -0.46
    lwjgl
    -0.45
     Vivi
    -0.44
     Bering
    -0.44
     tami
    -0.44
    POSITIVE LOGITS
    WithIOException
    0.72
     AssemblyCompany
    0.66
    Personensuche
    0.62
    bParam
    0.59
    RTSN
    0.59
    PhysRev
    0.57
    displayquote
    0.54
    MethodInfo
    0.54
    RTCK
    0.54
    atars
    0.53
    Activations Density 0.001%

    No Known Activations