© 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. 1438
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "G" at the beginning of words or abbreviations

    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
    wieś
    -0.67
    GEBURTSDATUM
    -0.55
     Immediate
    -0.53
     Gegenteil
    -0.52
    PrivateRoute
    -0.52
     viewType
    -0.51
     perfect
    -0.51
    perfect
    -0.51
     /\.
    -0.50
    esModule
    -0.50
    POSITIVE LOGITS
     >=",
    0.66
    roppo
    0.59
     oog
    0.55
     gynnwys
    0.54
     stresses
    0.53
     Lorca
    0.52
    FundMe
    0.51
    ponses
    0.51
     jaunes
    0.51
    localisation
    0.50
    Activations Density 0.473%

    No Known Activations