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. 15514
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or coding syntax involving comparison operators

    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
     ++;
    -0.61
    alanta
    -0.59
     Wiktionnaire
    -0.58
    Cordialement
    -0.58
     nahilalakip
    -0.57
     оригіналу
    -0.57
     Kork
    -0.57
     محفوظة
    -0.57
     ||=
    -0.56
    [++
    -0.55
    POSITIVE LOGITS
     gyhoeddwyd
    0.77
    IUrlHelper
    0.72
    DockStyle
    0.68
     protoimpl
    0.57
     gynhyrchwyd
    0.54
    LabelTagHelper
    0.54
    UnusedPrivate
    0.53
    protoimpl
    0.48
    tagHelperRunner
    0.48
    èlement
    0.47
    Activations Density 0.009%

    No Known Activations