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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26073
    Prev
    Next
    INDEX
    Explanations

    terms related to communication and data transfer

    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
     duquel
    -0.47
     
    -0.46
    ↵↵
    -0.45
    ↵
    -0.40
    cambi
    -0.40
    Britannique
    -0.40
     détermin
    -0.38
     coti
    -0.37
    hofen
    -0.37
    rettet
    -0.37
    POSITIVE LOGITS
    تقاوى
    0.88
    kháu
    0.85
    IVEREF
    0.81
    DockStyle
    0.78
    ValueStyle
    0.77
     ModelExpression
    0.77
    XmlAccessType
    0.77
    CppCodeGen
    0.73
     ThemeData
    0.72
     الاطلاع
    0.71
    Activations Density 0.305%

    No Known Activations