© 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. 17074
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols used 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
    Negative Logits
    gridx
    -0.45
     ratio
    -0.43
    CONTINUE
    -0.42
    getValueAt
    -0.42
     ambientale
    -0.42
     hozzá
    -0.41
    :+:
    -0.41
    stanz
    -0.40
     densité
    -0.39
     ratios
    -0.39
    POSITIVE LOGITS
    BeginContext
    0.94
     חיצוניים
    0.72
    EndContext
    0.71
     يتيمه
    0.70
     Roskov
    0.70
    AccessorTable
    0.69
     समीक्षक
    0.66
    CppCodeGen
    0.65
    UnknownFields
    0.65
    外部链接
    0.64
    Activations Density 0.330%

    No Known Activations