© 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. 22245
    Prev
    Next
    INDEX
    Explanations

    chemical elements and compounds, particularly in scientific contexts

    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
    Portale
    -0.67
     NSCoder
    -0.66
     समीक्षक
    -0.63
     beginnetje
    -0.63
    Portail
    -0.62
    ftagPool
    -0.61
     تانيه
    -0.60
    InjectAttribute
    -0.59
     MainAxisSize
    -0.59
    matchCondition
    -0.58
    POSITIVE LOGITS
    tvguidetime
    0.82
    abay
    0.52
    MENAFN
    0.52
    出版年
    0.50
    ----</
    0.49
    Kanpo
    0.48
    RAW
    0.48
    ernet
    0.47
    ]--;
    0.47
     actionMode
    0.47
    Activations Density 0.442%

    No Known Activations