© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 11405
    Prev
    Next
    INDEX
    Explanations

    the term "bound" in various contexts, often in relation to states or conditions

    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
    évaluateur
    -0.81
    WriteTagHelper
    -0.81
     nahilalakip
    -0.79
    insatz
    -0.77
    principalTable
    -0.75
    WEBPACK
    -0.74
     egret
    -0.73
     jLabel
    -0.70
     AssemblyTitle
    -0.70
    webElementGuid
    -0.69
    POSITIVE LOGITS
     Bound
    1.48
    Bound
    1.42
     bound
    1.35
    BOUND
    1.30
     BOUND
    1.29
    bound
    1.27
     bounds
    1.27
    bounds
    1.20
     Bounds
    1.13
    Bounds
    1.03
    Activations Density 0.014%

    No Known Activations