© 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. 18467
    Prev
    Next
    INDEX
    Explanations

    abbreviations or single-letter symbols commonly used in scientific contexts

    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
    a
    -0.67
    t
    -0.62
    anadas
    -0.61
    e
    -0.59
    d
    -0.59
    o
    -0.59
    >{@
    -0.57
     asegurarse
    -0.57
    r
    -0.57
     AssemblyTitle
    -0.56
    POSITIVE LOGITS
     pleaſure
    0.97
     Monfieur
    0.96
     itſelf
    0.95
     Conſ
    0.92
     Eſ
    0.91
     Anſ
    0.91
     myſelf
    0.91
     Efq
    0.88
    wiſe
    0.88
     ་་
    0.88
    Activations Density 0.131%

    No Known Activations