© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30897
    Prev
    Next
    INDEX
    Explanations

    significant identifiers or labels that denote responses or evaluations, particularly in a structured format

    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
    Negative Logits
    areth
    -0.52
    </strong>
    -0.52
     zvuky
    -0.51
    PageContext
    -0.49
    onicus
    -0.49
    しかったです
    -0.48
     preocupes
    -0.48
     partant
    -0.48
     préfé
    -0.47
     berarti
    -0.46
    POSITIVE LOGITS
     unknownFields
    0.84
    __":
    0.83
     ProtoMessage
    0.81
    oredCriteria
    0.79
     @"/
    0.78
    FunctionFlags
    0.77
    intios
    0.75
    KURZBESCHREIBUNG
    0.75
    OGND
    0.75
    principalTable
    0.75
    Activations Density 0.074%

    No Known Activations