© 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. 2-RES-MATRYOSHKA-DC
    7. 6045
    Prev
    Next
    INDEX
    Explanations

    references to specific HTML or markup code segments

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.52
    yer
    -0.44
    le
    -0.44
    avr
    -0.44
    府
    -0.42
    fromnode
    -0.42
     het
    -0.41
     democra
    -0.41
    liato
    -0.40
     मह
    -0.40
    POSITIVE LOGITS
    blockList
    6.28
     BLOCK
    1.39
     Block
    1.36
     block
    1.34
     Blocks
    1.32
    Block
    1.31
     blocks
    1.30
    BLOCK
    1.30
    block
    1.27
    Blocks
    1.23
    Activations Density 0.001%

    No Known Activations