© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14263
    Prev
    Next
    INDEX
    Explanations

    terms related to financial deposits

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    Initializable
    -0.73
    neurial
    -0.73
    Ordinal
    -0.66
     McFar
    -0.65
     Bren
    -0.63
    runner
    -0.63
    dimethy
    -0.63
     Rana
    -0.62
    avir
    -0.62
     racc
    -0.61
    POSITIVE LOGITS
     deposit
    1.70
     Deposit
    1.66
     DEPOSIT
    1.64
     Deposits
    1.62
     deposits
    1.60
     deposited
    1.55
    deposit
    1.49
     DEPOS
    1.44
    Deposits
    1.44
    Deposit
    1.42
    Activations Density 0.007%

    No Known Activations