© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 195
    Prev
    Next
    INDEX
    Explanations

    words associated with a financial loan process, especially online lending with bad credit

    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
     ("
    -0.65
    ?!?
    -0.65
    YMMV
    -0.63
     Mahomet
    -0.61
     egregious
    -0.60
     eventualmente
    -0.59
     (“
    -0.58
     potentially
    -0.58
    potentially
    -0.57
    redacted
    -0.57
    POSITIVE LOGITS
     upto
    1.02
     equipments
    1.01
     irrespective
    0.98
    noOf
    0.96
     till
    0.96
     hence
    0.96
    upto
    0.93
     Hence
    0.92
    Hence
    0.90
     atleast
    0.90
    Activations Density 4.847%

    No Known Activations