© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21908
    Prev
    Next
    INDEX
    Explanations

    topics related to geological and environmental factors

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     estekak
    -0.75
     AssemblyTitle
    -0.66
     transfieras
    -0.65
    expandindo
    -0.56
    IndentedString
    -0.56
     propOrder
    -0.55
    脚注の使い方
    -0.55
     виправивши
    -0.55
    EndProject
    -0.55
     CanadaChoose
    -0.53
    POSITIVE LOGITS
    ----</
    0.60
    aarrggbb
    0.56
    PathVariable
    0.52
    PackageInfo
    0.52
     ldc
    0.50
    万美元
    0.50
    imar
    0.49
     متحده
    0.49
     Normdatei
    0.49
    Allgemeine
    0.47
    Activations Density 0.536%

    No Known Activations