© 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. 22238
    Prev
    Next
    INDEX
    Explanations

    terms related to long-term depression (LTD) and its induction mechanisms in synaptic function

    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
    IntoConstraints
    -0.71
    DebuggerStep
    -0.71
     BIBSYS
    -0.69
    RUnlock
    -0.67
     ISNI
    -0.66
    Према
    -0.63
     GenerationType
    -0.62
     مشارکت‌کنندگان
    -0.60
    DotNetBar
    -0.60
     lenker
    -0.59
    POSITIVE LOGITS
     Griswold
    0.54
     estekak
    0.52
     forfait
    0.51
    learning
    0.49
     memoria
    0.49
     learning
    0.48
    chner
    0.48
     horseshoe
    0.47
    DeleteMapping
    0.46
     protocole
    0.46
    Activations Density 0.047%

    No Known Activations