© 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. 12-RES-MATRYOSHKA-DC
    7. 18441
    Prev
    Next
    INDEX
    Explanations

    symbolic representations of percentages or ratios

    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
    TestBed
    -0.79
    ioutil
    -0.70
     estimés
    -0.69
     blumen
    -0.69
    QtWidgets
    -0.64
     Kluwer
    -0.63
    //-----
    -0.63
    رشف
    -0.62
     httpClient
    -0.62
    drawiam
    -0.61
    POSITIVE LOGITS
    ã
    1.54
     ã
    1.10
     Tama
    0.82
    ãs
    0.78
    ãn
    0.75
    enderror
    0.72
    Tama
    0.69
     Linn
    0.67
    ĩ
    0.66
     Pend
    0.65
    Activations Density 0.000%

    No Known Activations