© 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. 1-RES-MATRYOSHKA-DC
    7. 431
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinion or belief

    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
    lidae
    -0.62
    ExecuteReader
    -0.47
    ע
    -0.45
     mudah
    -0.44
    Mea
    -0.44
     Audiodateien
    -0.43
     tudo
    -0.43
     OMITBAD
    -0.43
    andes
    -0.43
    gien
    -0.43
    POSITIVE LOGITS
     think
    4.16
     Think
    3.73
    Think
    3.73
    think
    3.70
     THINK
    3.63
     thinks
    3.38
     thought
    3.30
    THINK
    3.25
     Thought
    3.03
     thinking
    2.98
    Activations Density 0.612%

    No Known Activations