Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 9756
    Prev
    Next
    INDEX
    Explanations

    historical references related to military personnel and units

    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
     насељу
    -0.54
    ngoing
    -0.51
    AutoScaleMode
    -0.50
    PropertyChanging
    -0.49
    вни
    -0.48
    })`
    -0.48
     chez
    -0.47
    Revenir
    -0.47
     Powered
    -0.47
    Vegeu
    -0.45
    POSITIVE LOGITS
    ſelf
    0.63
     tslint
    0.61
     ſeveral
    0.61
     Lagu
    0.61
     Wallflower
    0.60
     initComponents
    0.59
     ſever
    0.59
    LabelTagHelper
    0.59
    ंदीखरीदारी
    0.58
     Partagez
    0.58
    Activations Density 0.071%

    No Known Activations