© 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. 2582
    Prev
    Next
    INDEX
    Explanations

    details about rankings and comparisons in competitive contexts

    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
    ällor
    -0.50
     hom
    -0.49
    RectangleBorder
    -0.49
    ∋
    -0.49
     potential
    -0.48
     common
    -0.47
     anch
    -0.47
     semej
    -0.47
     addition
    -0.46
    risse
    -0.46
    POSITIVE LOGITS
     superiority
    0.76
     supremacy
    0.74
    WithIOException
    0.71
    SharedDtor
    0.71
     dominates
    0.67
     dominate
    0.67
     dominating
    0.66
    rrggbb
    0.66
    kover
    0.66
     predominate
    0.65
    Activations Density 0.637%

    No Known Activations