© 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. 1-RES-MATRYOSHKA-DC
    7. 513
    Prev
    Next
    INDEX
    Explanations

    measurements related to force or force generation

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.56
    richt
    -0.56
    callee
    -0.54
     StyleSheet
    -0.54
     depreciation
    -0.54
    lä
    -0.53
     dó
    -0.53
     nakalista
    -0.53
    masalahan
    -0.52
     GoogleFonts
    -0.52
    POSITIVE LOGITS
     force
    4.97
     Force
    4.47
    force
    4.44
    Force
    4.25
     FORCE
    4.22
    FORCE
    3.69
     forces
    3.56
    forces
    3.34
     Forces
    3.31
    Forces
    3.19
    Activations Density 0.110%

    No Known Activations