© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 563
    Prev
    Next
    INDEX
    Explanations

    the word "decision" and words associated with it

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    曖昧さ回避
    -0.68
     disambiguazione
    -0.64
    idespread
    -0.58
    biome
    -0.57
    currents
    -0.57
    mployed
    -0.55
    gyz
    -0.55
    ttino
    -0.55
    uckles
    -0.55
    ored
    -0.55
    POSITIVE LOGITS
     Decision
    1.13
     decision
    1.09
     DECISION
    1.07
    Decision
    1.04
     Decisions
    1.02
    decision
    0.99
     decisions
    0.98
    Decisions
    0.91
     decided
    0.91
     Decide
    0.88
    Activations Density 0.123%

    No Known Activations