© 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. 26688
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical constraints and optimization in data analysis

    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
    kloped
    -0.80
     فريبيس
    -0.73
    })));
    -0.68
     ModelExpression
    -0.68
    PyExc
    -0.67
    setVerticalGroup
    -0.63
     للمعارف
    -0.62
    rawdę
    -0.62
    SequentialGroup
    -0.61
    ImageContext
    -0.61
    POSITIVE LOGITS
    mybatisplus
    0.63
     aient
    0.55
    ByPrimaryKey
    0.54
     ujednoznacz
    0.54
     oyuncu
    0.53
     devaient
    0.52
     piede
    0.51
     signé
    0.50
    parsedMessage
    0.49
     concernés
    0.49
    Activations Density 0.134%

    No Known Activations