© 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. 19640
    Prev
    Next
    INDEX
    Explanations

    terms related to neurons

    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
    ToBounds
    -0.63
    żdż
    -0.63
    CppMethod
    -0.61
    Royce
    -0.57
    helle
    -0.57
    ^-
    -0.56
     مرئيه
    -0.56
     Hel
    -0.55
    ToRemove
    -0.55
    }^{-\
    -0.55
    POSITIVE LOGITS
     neurons
    1.23
    neurons
    1.11
    urons
    1.10
    neuron
    1.05
     Neuron
    1.02
     neuron
    0.98
     Hike
    0.85
    Neuron
    0.85
     SPIE
    0.77
     MacGregor
    0.77
    Activations Density 0.005%

    No Known Activations