© 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. 12096
    Prev
    Next
    INDEX
    Explanations

    relationships and connections between events and concepts

    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
    brainly
    -0.66
    PhysRevD
    -0.63
    CodedInputStream
    -0.60
    damente
    -0.59
    XtraGrid
    -0.58
    varande
    -0.58
    jell
    -0.57
     iArr
    -0.57
    }?>
    -0.56
    Revenir
    -0.56
    POSITIVE LOGITS
    potranspiration
    0.55
    amerikanischer
    0.50
    strptime
    0.47
     JTable
    0.47
    tzmann
    0.46
     shru
    0.45
     skoro
    0.44
    PickerController
    0.44
     吋
    0.44
    wohner
    0.43
    Activations Density 0.080%

    No Known Activations