© 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. 1474
    Prev
    Next
    INDEX
    Explanations

    instances when there is a "B" followed by other characters

    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
     Winaray
    -0.70
    declarations
    -0.58
    atguigu
    -0.52
     erfol
    -0.52
    ulose
    -0.49
    Overhead
    -0.48
     prosi
    -0.48
     erkennt
    -0.47
    erm
    -0.47
    Mocks
    -0.47
    POSITIVE LOGITS
     bVar
    0.70
    ampton
    0.56
     Birds
    0.54
    GEBURTSDATUM
    0.54
    browserify
    0.52
     defaultstate
    0.52
    cove
    0.51
    })()
    0.50
     joc
    0.50
     виправивши
    0.50
    Activations Density 0.765%

    No Known Activations