© 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. 6026
    Prev
    Next
    INDEX
    Explanations

    references to authoritative sources related to truth and integrity

    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
     autorytatywna
    -0.49
    RegressionTest
    -0.47
    "]);
    -0.45
    原始内容存档于
    -0.44
    Personendaten
    -0.42
     }}^{
    -0.41
    age
    -0.40
     astore
    -0.40
    </thead>
    -0.39
     thus
    -0.38
    POSITIVE LOGITS
     Lightboxes
    0.76
    gonic
    0.66
    RUnlock
    0.65
     Geophysical
    0.65
    featureID
    0.65
    principalColumn
    0.63
    EndContext
    0.62
    posedge
    0.61
    unità
    0.61
    EndProject
    0.61
    Activations Density 0.273%

    No Known Activations