© 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. 0-RES-MATRYOSHKA-DC
    7. 10820
    Prev
    Next
    INDEX
    Explanations

    references to a specific concept of the core or fundamental nature of something

    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
     myself
    -1.73
     yourself
    -1.38
    myself
    -1.37
     Myself
    -1.23
     ourselves
    -1.15
     personally
    -1.08
     himself
    -1.04
    Myself
    -1.02
    yourself
    -0.99
     Yourself
    -0.98
    POSITIVE LOGITS
     itself
    2.00
    itself
    1.75
     Itself
    1.36
     itſelf
    1.13
     AssemblyCompany
    0.82
    本身
    0.77
     gynhyrchwyd
    0.75
    Демографія
    0.70
    writeFieldEnd
    0.70
     betweenstory
    0.70
    Activations Density 0.007%

    No Known Activations