© 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. 29995
    Prev
    Next
    INDEX
    Explanations

    references to net values or metrics in data 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
     betweenstory
    -0.75
    Portail
    -0.73
     Efq
    -0.71
     समीक्षक
    -0.71
     Eura
    -0.71
     Jefus
    -0.71
     houſe
    -0.71
     raiſ
    -0.69
     ſever
    -0.69
     Reſ
    -0.67
    POSITIVE LOGITS
    出版年
    0.77
     effect
    0.63
    ReusableCell
    0.63
     đích
    0.62
     Lumia
    0.60
     butterknife
    0.59
     Norvège
    0.59
     effects
    0.59
     résult
    0.58
    lampe
    0.58
    Activations Density 0.002%

    No Known Activations