© 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. 2049
    Prev
    Next
    INDEX
    Explanations

    the number 2 and numbers with decimals

    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
    Autoritní
    -0.77
     فريبيس
    -0.75
    ionales
    -0.60
     ModelExpression
    -0.59
     Pingback
    -0.54
     становника
    -0.54
    はじめに
    -0.53
    PhysRevD
    -0.53
    ührung
    -0.53
    entrums
    -0.51
    POSITIVE LOGITS
    
    0.76
     disambiguazione
    0.62
     iNdEx
    0.60
    dot
    0.56
    pushFollow
    0.55
    nonatomic
    0.52
    IntoConstraints
    0.51
    ResumeLayout
    0.49
    ern
    0.49
     ویکی‌پدیا
    0.49
    Activations Density 0.163%

    No Known Activations