© 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. 12-RES-MATRYOSHKA-DC
    7. 4240
    Prev
    Next
    INDEX
    Explanations

    references to charitable actions and community service

    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
     propOrder
    -0.83
    WebVitals
    -0.73
     utafitiHapana
    -0.71
    TintMode
    -0.68
     незавершена
    -0.67
    Bronnen
    -0.66
    AnchorStyles
    -0.66
    ArrowToggle
    -0.65
    endrait
    -0.65
    LookAnd
    -0.64
    POSITIVE LOGITS
     [
    0.81
     basically
    0.67
     veldig
    0.63
     really
    0.61
     obviamente
    0.60
    basically
    0.56
     Basically
    0.55
     everybody
    0.54
    Basically
    0.54
     very
    0.53
    Activations Density 0.688%

    No Known Activations