© 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. 952
    Prev
    Next
    INDEX
    Explanations

    phrases in the first person expressing a need or attempt to do something

    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
     للمعارف
    -0.61
     TAMBÉM
    -0.60
    Enllaces
    -0.56
    /?
    -0.54
     additional
    -0.53
     חיצוניים
    -0.53
     حداقل
    -0.53
    보다
    -0.52
     Either
    -0.52
    رشف
    -0.52
    POSITIVE LOGITS
    createClass
    0.73
     recently
    0.68
    offsetof
    0.67
    recently
    0.67
     lately
    0.65
     récemment
    0.65
     recentemente
    0.59
    Recently
    0.58
     Recently
    0.57
    versy
    0.56
    Activations Density 0.587%

    No Known Activations