© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1131
    Prev
    Next
    INDEX
    Explanations

    terms related to force and mechanical interactions

    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
    StoryboardSegue
    -1.00
     Мексичка
    -0.95
    Portale
    -0.93
     doubtnut
    -0.92
     Ory
    -0.86
     utafitiHapana
    -0.86
    ^(@)
    -0.85
    abestanden
    -0.84
     Beagle
    -0.84
    UnsafeEnabled
    -0.83
    POSITIVE LOGITS
     force
    1.41
     Force
    1.33
    Force
    1.23
     FORCE
    1.23
    force
    1.20
     forces
    1.09
    FORCE
    1.07
     Forces
    1.06
    strong
    1.03
     Strong
    1.03
    Activations Density 0.858%

    No Known Activations