© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4390
    Prev
    Next
    INDEX
    Explanations

    mentions of protein degradation related to signaling pathways

    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
    jednoc
    -0.57
     Magda
    -0.53
     fiscale
    -0.52
    vak
    -0.52
     manslaughter
    -0.51
     φύ
    -0.51
    ciso
    -0.50
     lauk
    -0.50
     taban
    -0.49
     Mathias
    -0.48
    POSITIVE LOGITS
     degradation
    2.81
     Degradation
    2.67
     degrade
    2.47
    degradation
    2.38
     degra
    2.33
     degraded
    2.25
     degrading
    2.05
     degrad
    2.03
    degrad
    1.41
    gradation
    1.34
    Activations Density 0.014%

    No Known Activations