© 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. 2-RES-MATRYOSHKA-DC
    7. 4221
    Prev
    Next
    INDEX
    Explanations

    an intention or desire related to completing tasks

    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
     GenerationType
    -0.71
     End
    -0.60
     déploy
    -0.60
    supset
    -0.59
     Dorsey
    -0.59
    AccessorTable
    -0.58
    Occurs
    -0.57
    seits
    -0.57
    featureID
    -0.56
    ressible
    -0.56
    POSITIVE LOGITS
     finish
    3.03
     finished
    2.91
     finishing
    2.83
     finishes
    2.78
     Finish
    2.75
     FINISH
    2.73
    finish
    2.72
     Finished
    2.67
    Finish
    2.64
    finished
    2.56
    Activations Density 0.062%

    No Known Activations