© 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. 4912
    Prev
    Next
    INDEX
    Explanations

    statements expressing an intended objective or aim

    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
     aims
    -0.90
    Aim
    -0.86
     aim
    -0.81
     Aim
    -0.79
     Aims
    -0.75
     aimed
    -0.73
    Aims
    -0.71
    aim
    -0.62
     bertujuan
    -0.61
     aiming
    -0.59
    POSITIVE LOGITS
     goal
    1.83
    goal
    1.79
     Goal
    1.73
    Goal
    1.71
     GOAL
    1.59
    goals
    1.40
     goals
    1.30
    Goals
    1.29
     Goals
    1.28
     GOALS
    1.26
    Activations Density 0.009%

    No Known Activations