© 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. 18-RES-MATRYOSHKA-DC
    7. 1084
    Prev
    Next
    INDEX
    Explanations

    the word "bank" or a variation of it

    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.18.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.18.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
     StatefulWidget
    -0.60
    varande
    -0.59
     schre
    -0.59
     Hentet
    -0.56
    Jîn
    -0.56
    LEA
    -0.54
    middels
    -0.54
    PhysRev
    -0.54
    FailureListener
    -0.53
     lauter
    -0.53
    POSITIVE LOGITS
    Banks
    1.13
     Banks
    1.11
     banks
    1.10
    banks
    1.09
     BANK
    1.02
     bank
    0.98
     BANKS
    0.96
     bankers
    0.95
    bank
    0.93
     banking
    0.93
    Activations Density 0.087%

    No Known Activations