© 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. 7339
    Prev
    Next
    INDEX
    Explanations

    statements expressing intention or purpose

    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
     goals
    -1.02
    goals
    -0.98
     Goals
    -0.94
    Goals
    -0.85
     goal
    -0.81
     Goal
    -0.79
     GOALS
    -0.79
    goal
    -0.75
     GOAL
    -0.73
     objective
    -0.71
    POSITIVE LOGITS
     aim
    2.03
    Aim
    1.98
     Aim
    1.97
    aim
    1.77
     aimed
    1.72
     aims
    1.63
     aiming
    1.53
     Aims
    1.48
     AIM
    1.34
    AIM
    1.30
    Activations Density 0.010%

    No Known Activations