© 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. 12-RES-MATRYOSHKA-DC
    7. 8411
    Prev
    Next
    INDEX
    Explanations

    terms related to key features in data processing and immunology

    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
     tartalomajánló
    -0.72
    DebuggerNonUser
    -0.70
    +#+#
    -0.67
     bezeichneter
    -0.67
    SourceChecksum
    -0.65
     pleaſure
    -0.65
     الحره
    -0.62
     تضيفلها
    -0.62
    omock
    -0.60
     fubject
    -0.60
    POSITIVE LOGITS
     @"/
    0.49
    rtype
    0.47
     bevor
    0.46
    aline
    0.46
    AtIndexPath
    0.45
    olto
    0.44
    DataURL
    0.44
     AssemblyTitle
    0.43
     skall
    0.42
     alone
    0.42
    Activations Density 0.420%

    No Known Activations