© 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. 22555
    Prev
    Next
    INDEX
    Explanations

    terms related to inability or lack of functional capacity

    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
    pyplot
    -0.90
    monary
    -0.73
    :✨
    -0.69
     отношению
    -0.65
     that
    -0.63
    protobuf
    -0.63
    ↵↵
    -0.58
    eradish
    -0.57
     ProtoMessage
    -0.57
     .
    -0.56
    POSITIVE LOGITS
     myſelf
    1.41
     pleaſure
    1.32
     ſever
    1.23
     Diſ
    1.19
     ſeveral
    1.19
     whoſe
    1.18
     Efq
    1.17
     Reſ
    1.14
     reaſon
    1.13
     themſelves
    1.11
    Activations Density 0.023%

    No Known Activations