© 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. 16068
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations or administrative districts in Poland

    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
     CreateTagHelper
    -0.81
    __(/*!
    -0.79
    aloo
    -0.66
    AttributeSet
    -0.65
    rungsseite
    -0.59
    χρι
    -0.59
    UnitTesting
    -0.59
    refu
    -0.57
    jewództ
    -0.57
     NSCoder
    -0.56
    POSITIVE LOGITS
    MigrationBuilder
    0.65
    oredCriteria
    0.54
     betale
    0.47
    };
    0.46
    NoSuchAlgorithm
    0.45
     Findlay
    0.45
    γγε
    0.44
     Geraadpleegd
    0.44
    商品説明
    0.43
     "'");
    0.43
    Activations Density 0.047%

    No Known Activations