© 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. 11253
    Prev
    Next
    INDEX
    Explanations

    acknowledgments and references to contributions or sources

    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
    出版年
    -0.53
    SBATCH
    -0.45
     publiés
    -0.44
    simpleType
    -0.43
     لب
    -0.42
    ACHED
    -0.42
     дописавши
    -0.41
    ंदीखरीदारी
    -0.40
    CELONA
    -0.40
    fitrión
    -0.40
    POSITIVE LOGITS
     pinulongan
    0.66
     iprot
    0.58
    Portály
    0.57
    photobucket
    0.57
     урна
    0.56
     newOwner
    0.56
    Hochspringen
    0.56
     évêque
    0.56
    thanks
    0.55
    urlopen
    0.54
    Activations Density 0.070%

    No Known Activations