Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 10718
    Prev
    Next
    INDEX
    Explanations

    highly specific or technical terms related to scientific or academic contexts

    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
    料
    -0.40
    ub
    -0.39
     naro
    -0.39
     equivo
    -0.38
     orec
    -0.37
    maco
    -0.37
     defendant
    -0.37
     onOptions
    -0.37
     еды
    -0.36
     Middleton
    -0.35
    POSITIVE LOGITS
     BorderSide
    0.98
    ArrowToggle
    0.84
    localctx
    0.84
    migrationBuilder
    0.84
    Джерела
    0.81
    UnknownFieldSet
    0.80
    ]")]
    0.79
    IANGLES
    0.79
     <<<<<<<<<<<<<<
    0.77
     Conſ
    0.77
    Activations Density 0.009%

    No Known Activations