© 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. 28697
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving inverse images and dimensionality in algebraic geometry

    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
    DotNetBar
    -0.52
    тифика
    -0.41
     chat
    -0.41
    Scan
    -0.39
     prosegu
    -0.39
    跳舞
    -0.38
    はな
    -0.38
     pret
    -0.38
     Rot
    -0.38
     Moves
    -0.37
    POSITIVE LOGITS
    Personensuche
    0.91
    Personendaten
    0.84
     متعلقه
    0.79
     AssemblyCulture
    0.78
     فريبيس
    0.78
    +#+#
    0.78
    хьтан
    0.72
    windowFixed
    0.70
    IndentedString
    0.70
    INCREF
    0.69
    Activations Density 0.005%

    No Known Activations