© 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. 20041
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associated representations, particularly in mathematical or scientific contexts

    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
    es
    -0.94
    s
    -0.72
    ersch
    -0.65
    ments
    -0.63
    ES
    -0.61
    ات
    -0.60
     Aless
    -0.59
    est
    -0.59
    پرس
    -0.58
    عر
    -0.58
    POSITIVE LOGITS
    ¹
    1.09
    ⁰
    1.02
    ⁴
    0.98
    ⁵
    0.93
     Roskov
    0.92
    StoryboardSegue
    0.91
    ¹,
    0.90
    ⁹
    0.84
    ³
    0.82
     AssemblyCulture
    0.82
    Activations Density 0.001%

    No Known Activations