© 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. 2465
    Prev
    Next
    INDEX
    Explanations

    phrases about embarking on a new life path

    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
     EconPapers
    -0.54
    плом
    -0.47
    ItemBackground
    -0.46
    Jeografia
    -0.44
    apimachinery
    -0.43
    TestFixture
    -0.42
    IMPORTED
    -0.42
    loài
    -0.40
    esez
    -0.40
     couverture
    -0.40
    POSITIVE LOGITS
     path
    2.98
    path
    2.61
     paths
    2.56
     Path
    2.47
    Path
    2.38
     pathway
    2.34
     route
    2.20
     Paths
    2.20
     PATH
    2.16
     pathways
    2.13
    Activations Density 1.169%

    No Known Activations