© 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. 929
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with people asking for technical help

    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
     conceivably
    -0.63
    printStackTrace
    -0.60
     subsequently
    -0.60
     admittedly
    -0.60
     Subsequently
    -0.59
     invariably
    -0.57
    StringCopy
    -0.56
    THISDAY
    -0.55
     ostensibly
    -0.54
     altrett
    -0.53
    POSITIVE LOGITS
     resourceCulture
    0.76
     gonna
    0.74
    webElementXpaths
    0.70
     GONNA
    0.68
     oprot
    0.66
     Gonna
    0.63
    новниш
    0.62
    يكب
    0.61
     gave
    0.61
     prepare
    0.60
    Activations Density 1.693%

    No Known Activations