© 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. 22-RES-MATRYOSHKA-DC
    7. 2330
    Prev
    Next
    INDEX
    Explanations

    sentences beginning with "is to build something that..."

    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
    webElementGuid
    -0.63
     NUKAT
    -0.60
    FormTagHelper
    -0.57
    StructEnd
    -0.57
    tagHelperRunner
    -0.56
    Filmographie
    -0.56
    EndContext
    -0.54
    bcryptjs
    -0.54
    lastIndex
    -0.54
     übrigens
    -0.54
    POSITIVE LOGITS
     magari
    0.96
     something
    0.90
     someone
    0.89
    someone
    0.87
     somebody
    0.86
    something
    0.84
    Something
    0.83
     Something
    0.81
     irgende
    0.78
    Someone
    0.77
    Activations Density 2.274%

    No Known Activations