© 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. 5074
    Prev
    Next
    INDEX
    Explanations

    terms related to guidance or advice

    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
     Mok
    -0.66
    redhat
    -0.64
     Vill
    -0.62
    machung
    -0.61
    войства
    -0.61
     Hurst
    -0.60
     Zuckerberg
    -0.60
     Skar
    -0.60
    texttt
    -0.60
    抹
    -0.59
    POSITIVE LOGITS
     guides
    1.57
     guidance
    1.52
     guide
    1.46
    guide
    1.41
     Guides
    1.40
    guidance
    1.38
    Guide
    1.37
     guider
    1.35
     Guide
    1.34
     Guidance
    1.34
    Activations Density 0.119%

    No Known Activations