© 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. 1134
    Prev
    Next
    INDEX
    Explanations

    capitalized names in legal opinions and political articles

    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
     Autres
    -0.76
     zijne
    -0.60
     vulgaires
    -0.59
     Græ
    -0.58
    demás
    -0.57
     avoient
    -0.57
    webElementXpaths
    -0.56
     Verhält
    -0.56
    fromnode
    -0.52
    katakan
    -0.52
    POSITIVE LOGITS
    OGND
    0.76
     تضيفلها
    0.70
    DllImport
    0.59
    inflater
    0.59
    GenerationType
    0.57
    (!__
    0.57
    DotNetBar
    0.56
     &___
    0.54
     IndexPath
    0.54
    Inflater
    0.53
    Activations Density 0.688%

    No Known Activations