© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 22694
    Prev
    Next
    INDEX
    Explanations

    terms related to trajectories in various contexts

    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
     CommonModule
    -0.81
    انجليز
    -0.72
    бият
    -0.69
    pacs
    -0.67
    nocache
    -0.67
    стема
    -0.66
    nologue
    -0.66
     ostavi
    -0.65
     Laplacian
    -0.65
     Frances
    -0.63
    POSITIVE LOGITS
     Trajectory
    1.37
     trajectory
    1.33
     trajectories
    1.29
    jectories
    1.25
    Trajectory
    1.20
    trajectory
    1.17
    jectory
    0.89
    cmath
    0.78
     traj
    0.73
    setViewName
    0.73
    Activations Density 0.003%

    No Known Activations