© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11121
    Prev
    Next
    INDEX
    Explanations

    negative indicators or terms within statistical or analytical contexts

    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
     
    -0.93
     four
    -0.81
     three
    -0.75
     two
    -0.75
     five
    -0.74
     six
    -0.72
     the
    -0.67
     seven
    -0.67
     A
    -0.65
     in
    -0.64
    POSITIVE LOGITS
     utafitiHapana
    1.58
    GEBURTSDATUM
    1.31
     للاسماء
    1.24
    WebVitals
    1.23
    AccessorTable
    1.20
     ainfi
    1.19
     виправивши
    1.17
     оригіналу
    1.12
    OGND
    1.11
    rungsseite
    1.10
    Activations Density 0.236%

    No Known Activations