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. 16377
    Prev
    Next
    INDEX
    Explanations

    action verbs and commands related to handling and managing tasks or objects

    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
    +#+#
    -0.86
    localctx
    -0.75
    RectangleBorder
    -0.75
     NSCoder
    -0.75
    devamını
    -0.70
     createState
    -0.69
    bootstrapcdn
    -0.64
    dAtA
    -0.64
     BorderLayout
    -0.63
    ModelAdmin
    -0.61
    POSITIVE LOGITS
    signable
    0.55
    UnusedPrivate
    0.53
     جدا
    0.50
     ves
    0.49
     diffuse
    0.49
    hiers
    0.49
     sekali
    0.48
    präch
    0.47
    ország
    0.47
    条
    0.47
    Activations Density 0.043%

    No Known Activations