© 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. 30134
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and 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
    aarrggbb
    -0.98
    contentLoaded
    -0.85
     intptr
    -0.85
    NameInMap
    -0.84
    SharedCtor
    -0.82
    InstrumentedTest
    -0.82
     Réponses
    -0.77
    Personensuche
    -0.76
    CppMethod
    -0.75
    PreferredItem
    -0.73
    POSITIVE LOGITS
    γραφή
    0.46
     membersihkan
    0.44
     enkelt
    0.42
     was
    0.42
    unpublished
    0.42
     presumably
    0.40
    :^(
    0.39
     mucha
    0.38
     
    0.38
    labilir
    0.37
    Activations Density 0.071%

    No Known Activations