© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 374
    Prev
    Next
    INDEX
    Explanations

    Russian text or programming code that includes Russian.

    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
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.60
    IsPostBack
    -0.59
    êcher
    -0.54
    ТЕЛЬ
    -0.54
    henswürdigkeiten
    -0.52
    цездатний
    -0.52
    parsedMessage
    -0.52
    ЧЕСКИ
    -0.51
     Rukh
    -0.51
     démocratie
    -0.50
    POSITIVE LOGITS
     Poh
    0.45
     pain
    0.45
     pys
    0.42
     tied
    0.41
     suo
    0.41
     muita
    0.41
     nope
    0.40
     rhetorical
    0.40
     vai
    0.39
     historian
    0.39
    Activations Density 0.298%

    No Known Activations