© 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. 28428
    Prev
    Next
    INDEX
    Explanations

    noun phrases that are likely introductory or subject-focused in scientific or technical 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
     Ketch
    -0.91
     Syna
    -0.73
    <?,
    -0.72
    cydow
    -0.70
     Arra
    -0.66
    ểm
    -0.65
    eriam
    -0.65
    //<
    -0.64
     Esch
    -0.64
     Bein
    -0.64
    POSITIVE LOGITS
     NP
    1.50
     NPs
    1.48
    NP
    1.25
    NPs
    1.02
     nakalista
    0.92
     PNP
    0.90
     NPY
    0.82
     ModelExpression
    0.81
     تانيه
    0.81
    FFFFFFFF
    0.80
    Activations Density 0.004%

    No Known Activations