© 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. 7072
    Prev
    Next
    INDEX
    Explanations

    references to stability or being in a stable state

    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
     eventuali
    -0.59
    ="#"><
    -0.57
    اشت
    -0.56
    ****************
    -0.53
     pemuda
    -0.51
    ardez
    -0.49
    tryk
    -0.47
     morire
    -0.47
    intre
    -0.47
    *((
    -0.47
    POSITIVE LOGITS
     stable
    2.72
     Stable
    2.55
    stable
    2.41
    Stable
    2.41
     stables
    1.77
     stabile
    1.34
    稳定的
    1.13
     стаби
    1.06
     unstable
    1.04
    unstable
    1.02
    Activations Density 0.007%

    No Known Activations