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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19349
    Prev
    Next
    INDEX
    Explanations

    terms related to kinetic energy and motion

    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
    ctivity
    -0.58
     οποίο
    -0.57
    Scho
    -0.57
     stability
    -0.56
     stabile
    -0.55
     Scho
    -0.54
    hody
    -0.54
    ooga
    -0.54
     Bergen
    -0.53
     Schon
    -0.53
    POSITIVE LOGITS
    kinetic
    1.31
    Kinetic
    1.27
     Kinetic
    1.27
     kinetic
    1.25
     kinetics
    1.00
     saites
    0.94
    FunctionFlags
    0.90
     Kinetics
    0.90
    IntoConstraints
    0.88
    Lähteet
    0.85
    Activations Density 0.004%

    No Known Activations