© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10391
    Prev
    Next
    INDEX
    Explanations

    references to historical or etymological aspects of names related to trees or woodlands

    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
    Negative Logits
    GEBURTSDATUM
    -0.52
    hood
    -0.45
    __(/*!
    -0.44
     NotImplemented
    -0.43
    ServiceName
    -0.42
     pensato
    -0.42
     espirituales
    -0.41
    olithic
    -0.41
     name
    -0.40
    ྣ
    -0.40
    POSITIVE LOGITS
     estekak
    0.71
     Normdatei
    0.69
    __':
    0.65
     referenties
    0.65
    windowFixed
    0.64
     /\.
    0.63
    XmlAccessType
    0.63
     getItemId
    0.63
    SourceChecksum
    0.63
    ]")]
    0.62
    Activations Density 0.005%

    No Known Activations