© 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. 31026
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or variables related to parameter representation in equations

    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
    Personensuche
    -0.88
    rungsseite
    -0.84
    Datuak
    -0.82
    OGND
    -0.78
    BASEPATH
    -0.73
    帖最后由
    -0.73
    findpost
    -0.72
    GEBURTS
    -0.70
    省市镇
    -0.68
     betweenstory
    -0.68
    POSITIVE LOGITS
    CommandText
    0.55
     finite
    0.53
    RetentionPolicy
    0.52
     highlight
    0.47
     Financi
    0.46
     کال
    0.46
     שנים
    0.45
    รร
    0.45
    kej
    0.44
    ningss
    0.44
    Activations Density 0.025%

    No Known Activations