© 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. 16001
    Prev
    Next
    INDEX
    Explanations

    references to factual assertions and their validity

    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
    Not in Any Lists

    No Comments

    Negative Logits
     springfox
    -0.77
     المعيارى
    -0.74
    etheless
    -0.69
    daß
    -0.68
    multicolumn
    -0.66
    .$.
    -0.65
    AddRange
    -0.65
     fact
    -0.64
     Packard
    -0.62
    lynol
    -0.61
    POSITIVE LOGITS
    ArgsConstructor
    0.74
    出版年
    0.59
     ActivatedRoute
    0.55
     szen
    0.55
     serce
    0.54
     initComponents
    0.54
    okovic
    0.52
    fhir
    0.52
     privées
    0.51
     isothermal
    0.51
    Activations Density 0.013%

    No Known Activations