© 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. 24-RES-MATRYOSHKA-DC
    7. 1591
    Prev
    Next
    INDEX
    Explanations

    technical language about mathematical systems

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    PreExecute
    -0.62
    InSection
    -0.60
    SerializedSize
    -0.58
    enoord
    -0.56
     novios
    -0.54
    parian
    -0.54
    ẹo
    -0.53
    )_/¯
    -0.52
    contentLoaded
    -0.51
    rairie
    -0.51
    POSITIVE LOGITS
     dynamics
    0.85
     Dynamics
    0.75
     dynamical
    0.74
    dynamics
    0.72
    Dynamics
    0.69
    YNAMICS
    0.67
    Демографія
    0.60
     chaotic
    0.60
     dynamic
    0.59
     bist
    0.59
    Activations Density 1.168%

    No Known Activations