© 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. 29993
    Prev
    Next
    INDEX
    Explanations

    statements indicating the goals or importance of research

    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
    +#+#
    -1.26
     المعيارى
    -1.21
    ContentAsync
    -0.93
    parsedMessage
    -0.92
     متعلقه
    -0.92
    ArgsConstructor
    -0.86
     Савезне
    -0.84
    esModule
    -0.82
    IVEREF
    -0.82
     tartalomajánló
    -0.81
    POSITIVE LOGITS
     "
    0.50
     op
    0.44
     '
    0.43
     Barangay
    0.43
     pastillas
    0.43
     meto
    0.42
    Paragraph
    0.42
    وا
    0.42
     arra
    0.42
     total
    0.42
    Activations Density 0.028%

    No Known Activations