© 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. 24-RES-MATRYOSHKA-DC
    7. 1026
    Prev
    Next
    INDEX
    Explanations

    error messages and code snippets related to neural networks

    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.24.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.24.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
    yntaxException
    -0.54
    ❉
    -0.54
     nahilalakip
    -0.53
    xase
    -0.52
    ++];
    -0.52
    cicle
    -0.52
     Pritchard
    -0.51
    Спољашње
    -0.51
    QMetaType
    -0.51
    ändler
    -0.50
    POSITIVE LOGITS
     relu
    0.63
     layer
    0.62
    SequentialGroup
    0.61
     批
    0.59
     activation
    0.57
    Layer
    0.57
    relu
    0.57
     Layer
    0.57
    layer
    0.56
     layers
    0.55
    Activations Density 0.276%

    No Known Activations