© 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. 22-RES-MATRYOSHKA-DC
    7. 3273
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the words "based on"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    endphp
    -0.56
     anlam
    -0.56
    ("}");
    -0.54
    ểu
    -0.53
     Extragalactic
    -0.52
     noqa
    -0.52
    Karriere
    -0.51
    chowa
    -0.50
     Wikimedijinoj
    -0.50
    頃は
    -0.50
    POSITIVE LOGITS
     assumption
    0.95
     principles
    0.90
     assumptions
    0.90
    principles
    0.79
     premise
    0.79
     observations
    0.75
     knowledge
    0.74
     considerations
    0.74
    assumption
    0.72
     analogy
    0.69
    Activations Density 0.630%

    No Known Activations