© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4070
    Prev
    Next
    INDEX
    Explanations

    structured references to specific points or data in a document

    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
     HasFactory
    -0.96
    ChildScrollView
    -0.84
     MainAxisSize
    -0.79
    Autoritní
    -0.78
    expandindo
    -0.76
     Theſe
    -0.76
     DELLE
    -0.76
    ercito
    -0.75
    CORBA
    -0.75
    IsMutable
    -0.72
    POSITIVE LOGITS
     POINT
    1.69
     point
    1.63
     Point
    1.57
     points
    1.56
    point
    1.55
    POINT
    1.52
     Points
    1.45
    Point
    1.44
    points
    1.43
     POINTS
    1.41
    Activations Density 0.286%

    No Known Activations