© 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. 1872
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing possibility

    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
    tagHelper
    -0.65
     ujednoznacz
    -0.64
     contain
    -0.63
     muualla
    -0.60
     prove
    -0.60
     belong
    -0.60
    Chham
    -0.59
    RegistryLite
    -0.59
     Référence
    -0.59
     represent
    -0.58
    POSITIVE LOGITS
     be
    1.10
     être
    1.08
     being
    1.03
     být
    1.01
     быть
    0.97
     essere
    0.95
    被
    0.91
     бути
    0.88
    being
    0.88
     soient
    0.87
    Activations Density 0.647%

    No Known Activations