© 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. 22-RES-MATRYOSHKA-DC
    7. 1898
    Prev
    Next
    INDEX
    Explanations

    mathematical terms, in particular equations approaching a limit.

    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.22.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.22.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
    tagHelperRunner
    -0.72
    MigrationBuilder
    -0.65
    SourceChecksum
    -0.60
     kasarigan
    -0.59
     насељу
    -0.58
     pinulongan
    -0.57
     مشين
    -0.57
    imeter
    -0.57
    évaluateur
    -0.56
     ostavi
    -0.55
    POSITIVE LOGITS
     zero
    2.08
    zero
    1.73
     Zero
    1.67
     ZERO
    1.64
    Zero
    1.58
     zéro
    1.55
     cero
    1.50
    ZERO
    1.47
     null
    1.41
     zeros
    1.32
    Activations Density 2.322%

    No Known Activations