© 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. 1451
    Prev
    Next
    INDEX
    Explanations

    references to external links or connections

    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
     تضيفلها
    -0.98
    harusnya
    -0.74
     censo
    -0.71
    esgue
    -0.69
    rophoresis
    -0.69
    mobileqq
    -0.68
    ContentLoaded
    -0.68
     Pliocene
    -0.67
     fotográfico
    -0.65
     opcode
    -0.65
    POSITIVE LOGITS
     outside
    1.43
    outside
    1.41
     Outside
    1.38
    External
    1.34
    Outside
    1.31
     OUTSIDE
    1.30
     external
    1.29
     External
    1.29
    OUTSIDE
    1.24
     extern
    1.23
    Activations Density 0.237%

    No Known Activations