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. 22364
    Prev
    Next
    INDEX
    Explanations

    negative sentiment expressions or indicators

    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
     CreateTagHelper
    -0.74
    EDEFAULT
    -0.71
     TIR
    -0.66
     ToString
    -0.65
    ";}
    -0.63
    פיל
    -0.63
    chehen
    -0.61
    MessageTagHelper
    -0.61
     LEYENDO
    -0.60
     autorytatywna
    -0.60
    POSITIVE LOGITS
     EconPapers
    0.58
    principalTable
    0.55
    mybatisplus
    0.50
     Vikipedi
    0.47
     tramonto
    0.45
     kerst
    0.45
     humming
    0.45
     Schwangerschaft
    0.45
    ItemBackground
    0.45
    LookAnd
    0.43
    Activations Density 0.001%

    No Known Activations