© 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. 3287
    Prev
    Next
    INDEX
    Explanations

    references to planets or the word "planets"

    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
     environment
    -0.48
     اسلام
    -0.47
     Umgebung
    -0.47
    Light
    -0.47
    star
    -0.46
     miljö
    -0.46
    light
    -0.46
     Environment
    -0.46
    environment
    -0.45
     Environmental
    -0.44
    POSITIVE LOGITS
     planet
    2.61
     planets
    2.53
    planet
    2.31
     Planet
    2.30
     PLANET
    2.25
     Planets
    2.22
    Planet
    2.13
    planets
    1.92
     Planeten
    1.84
     planète
    1.83
    Activations Density 0.014%

    No Known Activations