© 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. 3-RES-MATRYOSHKA-DC
    7. 2849
    Prev
    Next
    INDEX
    Explanations

    the concept of balance, sometimes in the context of tradeoffs

    oai_token-act-pair · gemini-2.0-flash
    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
     rente
    -0.55
    клопе
    -0.52
    rungsseite
    -0.51
    pushFollow
    -0.51
     Hits
    -0.51
    出版年
    -0.51
     cobrar
    -0.50
    RTLD
    -0.50
     LIRE
    -0.50
    SuccessListener
    -0.49
    POSITIVE LOGITS
     balance
    3.56
     Balance
    3.38
    balance
    3.31
     balances
    3.17
    Balance
    3.13
     BALANCE
    3.03
     balancing
    2.89
    BALANCE
    2.86
    balances
    2.83
     balanced
    2.80
    Activations Density 0.051%

    No Known Activations