© 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. 16352
    Prev
    Next
    INDEX
    Explanations

    terms related to volatility in contexts associated with finance or risk

    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
    +#+
    -0.71
     kepad
    -0.63
     tutt
    -0.61
    eriksaan
    -0.60
    cB
    -0.59
    ஆ
    -0.58
    باش
    -0.56
     pihaknya
    -0.56
     sempurna
    -0.56
     referenties
    -0.56
    POSITIVE LOGITS
     Volatile
    1.41
    Volatile
    1.40
     volatile
    1.29
     volatility
    1.25
     Volatility
    1.24
    volatile
    1.21
    atiles
    1.15
    ATILE
    1.05
    atility
    0.97
     vola
    0.94
    Activations Density 0.001%

    No Known Activations