© 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. 10793
    Prev
    Next
    INDEX
    Explanations

    phrases related to insurance policies and promotional offers

    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
     saites
    -0.78
    IContainer
    -0.64
    OGND
    -0.62
    ArrowToggle
    -0.61
    UserScript
    -0.60
     ब्रेकडाउन
    -0.59
    :///
    -0.58
     Obrador
    -0.58
    UnknownFieldSet
    -0.57
    });*/
    -0.56
    POSITIVE LOGITS
     resourceCulture
    0.63
     doInBackground
    0.53
    istung
    0.52
     Treue
    0.50
    lüğ
    0.46
    AndEndTag
    0.45
     fidélité
    0.45
     رض
    0.44
     satisfied
    0.44
     défi
    0.43
    Activations Density 0.101%

    No Known Activations