© 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. 31960
    Prev
    Next
    INDEX
    Explanations

    concepts related to formal structures or methodologies in various 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
    Negative Logits
    FunctionFlags
    -0.60
     MenuView
    -0.59
    leſs
    -0.57
    subpackage
    -0.56
    ItemBackground
    -0.56
     sign
    -0.55
    licet
    -0.54
    "])
    -0.54
    WithIOException
    -0.54
     ins
    -0.53
    POSITIVE LOGITS
     sahiptir
    0.61
     constitucional
    0.57
     sicura
    0.54
     raconter
    0.54
     mattina
    0.52
     directement
    0.52
     scurt
    0.52
    StoryboardSegue
    0.52
     incontr
    0.52
    summon
    0.51
    Activations Density 0.490%

    No Known Activations