© 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. 12-RES-MATRYOSHKA-DC
    7. 3804
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to contacting or reaching out for assistance

    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
    Artik
    -0.57
    atrième
    -0.56
    uther
    -0.51
     Square
    -0.48
     square
    -0.47
     miſ
    -0.45
    zsche
    -0.45
    PLAC
    -0.45
    katu
    -0.44
    ρεσ
    -0.44
    POSITIVE LOGITS
     StatefulWidget
    0.85
    contact
    0.81
    rungsseite
    0.78
    ArgsConstructor
    0.75
    Contact
    0.74
     StatelessWidget
    0.73
     unknownFields
    0.72
     contact
    0.71
    CONTACT
    0.70
     NSCoder
    0.69
    Activations Density 0.145%

    No Known Activations