© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5429
    Prev
    Next
    INDEX
    Explanations

    mentions of towns

    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
     Karlsruhe
    -0.67
     resultSet
    -0.65
    iegler
    -0.65
    arische
    -0.61
     Samos
    -0.60
    uesday
    -0.60
     Blätter
    -0.59
    aviar
    -0.59
    acias
    -0.59
    yler
    -0.59
    POSITIVE LOGITS
     Town
    1.12
     Towne
    1.10
     TOWN
    1.09
    Towns
    1.09
    town
    1.06
    Town
    1.05
     Townsend
    1.04
     towns
    1.03
    TOWN
    1.02
    AsUp
    1.02
    Activations Density 0.025%

    No Known Activations