© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15840
    Prev
    Next
    INDEX
    Explanations

    references to activation of the Akt signaling pathway

    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
    Datuak
    -0.89
    Snapshot
    -0.62
    SuccessListener
    -0.62
    names
    -0.61
     مشين
    -0.56
    orianCalendar
    -0.53
    Skocz
    -0.52
     crested
    -0.52
    egrave
    -0.51
     antena
    -0.51
    POSITIVE LOGITS
     AKT
    1.26
     Akt
    1.20
    Akt
    1.19
    AKT
    1.02
    Aber
    0.78
     aberrant
    0.71
     Aber
    0.70
     adipose
    0.61
    basicConfig
    0.59
    SPATH
    0.57
    Activations Density 0.004%

    No Known Activations