© 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. 24725
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or formulas related to scientific calculations

    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
     return
    -0.51
    apan
    -0.49
    <eos>
    -0.48
     Sch
    -0.47
     sch
    -0.46
     Me
    -0.45
     da
    -0.43
     meet
    -0.41
     v
    -0.40
     or
    -0.40
    POSITIVE LOGITS
    RegistryLite
    1.16
     Efq
    0.98
    WireFormatLite
    0.97
    tagHelperRunner
    0.92
    parametrize
    0.92
     Theſe
    0.90
    ConstraintMaker
    0.88
    EndContext
    0.84
     Shakspeare
    0.81
    ftagPool
    0.81
    Activations Density 0.019%

    No Known Activations