© 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. 3710
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to processes in manufacturing or engineering

    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
    кров
    -0.51
    arm
    -0.49
     trasferimento
    -0.47
     braccio
    -0.46
    Ultra
    -0.45
    ham
    -0.45
     simply
    -0.44
     Simply
    -0.43
    hev
    -0.42
    mar
    -0.42
    POSITIVE LOGITS
    Personendaten
    1.02
    GEBURTSDATUM
    0.98
     فريبيس
    0.94
    makeConstraints
    0.93
    ernalia
    0.88
    Билгалдахарш
    0.84
    addCriterion
    0.81
     AssemblyCulture
    0.81
    +:+
    0.80
    MigrationBuilder
    0.79
    Activations Density 0.425%

    No Known Activations