© 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. 54
    Prev
    Next
    INDEX
    Explanations

    formal legal terminology and procedural language

    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
    principalTable
    -1.15
     pinulongan
    -1.10
     виправивши
    -1.06
    XmlAccessType
    -1.02
    tvguidetime
    -0.99
    principalColumn
    -0.98
    GEBURTSDATUM
    -0.98
     wikipagina
    -0.96
    
    -0.96
     AssemblyCulture
    -0.96
    POSITIVE LOGITS
    In
    0.92
    The
    0.90
     In
    0.88
     The
    0.78
    As
    0.78
     As
    0.77
    For
    0.75
    To
    0.72
    At
    0.70
    This
    0.69
    Activations Density 6.747%

    No Known Activations