© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19385
    Prev
    Next
    INDEX
    Explanations

    references to sources or directions for further reading

    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
    enumi
    -0.53
    gathered
    -0.49
    iestety
    -0.49
     speaking
    -0.48
    Parcelable
    -0.47
     spoke
    -0.46
    uffe
    -0.46
    elemField
    -0.45
     gathered
    -0.44
    ISupport
    -0.43
    POSITIVE LOGITS
     للمعارف
    0.86
    expandindo
    0.74
     utafitiHapana
    0.63
     referenties
    0.63
    rzej
    0.63
     financeira
    0.63
    ConstraintMaker
    0.62
    AsUp
    0.62
    peq
    0.61
     lemn
    0.60
    Activations Density 0.004%

    No Known Activations