© 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. 22856
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical expressions

    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
    WriteTagHelper
    -0.83
     kasarigan
    -0.82
    UnknownFields
    -0.75
     protoimpl
    -0.71
    featureID
    -0.67
    AddTagHelper
    -0.67
    UnsafeEnabled
    -0.65
    StructEnd
    -0.65
     unknownFields
    -0.64
    findpost
    -0.63
    POSITIVE LOGITS
    UIControlState
    0.57
    typeorm
    0.54
    breasted
    0.49
    Ссылки
    0.47
    الدراسه
    0.44
    原始内容存档
    0.44
    ToTable
    0.43
     UnityEditor
    0.43
    CMAKE
    0.43
    ackerel
    0.43
    Activations Density 0.596%

    No Known Activations