© 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. 875
    Prev
    Next
    INDEX
    Explanations

    instances of comparison and contrast between different subjects or results

    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
    Hauptartikel
    -0.76
     Rosenberg
    -0.75
    NegativeButton
    -0.75
    EndGlobalSection
    -0.75
    igrette
    -0.74
     FontWeight
    -0.71
     برانيه
    -0.69
    AndEndTag
    -0.69
    entgen
    -0.69
     Wikispecies
    -0.69
    POSITIVE LOGITS
     compared
    1.42
     comparison
    1.36
     Comparisons
    1.36
     comparisons
    1.30
    compared
    1.27
     Compar
    1.25
     Comparison
    1.25
    compar
    1.24
     compares
    1.24
     Compared
    1.24
    Activations Density 0.179%

    No Known Activations