© 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. 9983
    Prev
    Next
    INDEX
    Explanations

    mathematical operations involving functions and parameters

    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
    Personensuche
    -0.73
    queryInterface
    -0.69
    tonode
    -0.68
    bootstrapcdn
    -0.63
    WebVitals
    -0.63
     resourceCulture
    -0.60
    Дереккөздер
    -0.60
    StructEnd
    -0.59
    andExpect
    -0.58
    #+#
    -0.57
    POSITIVE LOGITS
    raisers
    0.52
    ronique
    0.51
     CURIAM
    0.48
    ومه
    0.44
    diyesi
    0.44
    izient
    0.43
     eax
    0.43
    emu
    0.42
    abestanden
    0.42
    riturismo
    0.42
    Activations Density 0.017%

    No Known Activations