© 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. 32199
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "the" in various 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
     бампер
    -0.45
     puestos
    -0.41
     entorno
    -0.40
     Pe
    -0.40
     criptomonedas
    -0.40
     banho
    -0.39
    JOptionPane
    -0.39
     suerte
    -0.38
     lieux
    -0.37
     or
    -0.37
    POSITIVE LOGITS
     tartalomajánló
    1.08
    SharedCtor
    1.02
     endblock
    0.99
     дописавши
    0.86
    참고
    0.84
     Савезне
    0.84
    Personendaten
    0.84
    XmlAccessType
    0.83
    PreferredItem
    0.83
     مرئيه
    0.82
    Activations Density 0.027%

    No Known Activations