© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 21532
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in legal cases

    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
    XMLSchema
    -0.50
     attentes
    -0.47
     متعلقه
    -0.47
     CURIAM
    -0.47
     peines
    -0.46
    SBATCH
    -0.45
     juges
    -0.45
     useRouter
    -0.44
    เร็
    -0.44
    KommentareTeilen
    -0.44
    POSITIVE LOGITS
     Carrasco
    0.56
     imageNamed
    0.55
    مصادر
    0.54
     Break
    0.54
    ourite
    0.54
    onomía
    0.54
    IUrlHelper
    0.54
    threatening
    0.54
     Vgl
    0.52
    ländische
    0.52
    Activations Density 0.126%

    No Known Activations