© 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. 22-RES-MATRYOSHKA-DC
    7. 2167
    Prev
    Next
    INDEX
    Explanations

    code or technical specifications where inputs and outputs are processed

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    
    -0.66
    TagMode
    -0.57
     الرياضيه
    -0.52
    
    -0.51
     disso
    -0.50
    lepiej
    -0.50
    enschaften
    -0.49
     protoimpl
    -0.48
    übers
    -0.47
    Referències
    -0.47
    POSITIVE LOGITS
     input
    3.48
    input
    3.19
     Input
    2.92
    Input
    2.78
     INPUT
    2.48
     inputs
    2.44
    INPUT
    2.36
    输入
    2.20
     Inputs
    2.13
     output
    2.03
    Activations Density 0.281%

    No Known Activations