© 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. 17435
    Prev
    Next
    INDEX
    Explanations

    phrases indicating location or presence, especially in relation to structures and characters

    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
    complexType
    -0.73
    جمعیت
    -0.65
    complexContent
    -0.61
    MigrationBuilder
    -0.61
     дописавши
    -0.60
    Personendaten
    -0.57
    Aholisi
    -0.57
    kháu
    -0.57
    Rè
    -0.57
     GENERATED
    -0.56
    POSITIVE LOGITS
    newArrayList
    0.60
     فريبيس
    0.56
    råd
    0.56
    sorry
    0.52
     tartalomajánló
    0.50
     ComVisible
    0.50
     étoient
    0.49
     étrangères
    0.49
     متعلقه
    0.48
     createState
    0.47
    Activations Density 0.115%

    No Known Activations