© 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. 2262
    Prev
    Next
    INDEX
    Explanations

    mathematical notation (especially plus signs and exponents) surrounding a letter

    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
    存于互联网档案馆
    -0.46
    thmus
    -0.39
     Berman
    -0.38
     Bergh
    -0.38
     lễ
    -0.38
     Marina
    -0.36
     Hul
    -0.36
    seu
    -0.36
     Spicer
    -0.35
    Christ
    -0.35
    POSITIVE LOGITS
     q
    1.84
    q
    1.73
     Q
    1.66
    Q
    1.59
     Quality
    1.53
     quality
    1.46
    Quality
    1.46
    QUALITY
    1.44
     QUALITY
    1.43
     Quinn
    1.41
    Activations Density 0.868%

    No Known Activations