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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13994
    Prev
    Next
    INDEX
    Explanations

    the neuron specifically detects the concept of **"movable"** in context related to mechanical components or systems

    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
    LookAnd
    -0.72
    jsxFileName
    -0.59
    corpions
    -0.56
    eningrad
    -0.55
     magasiner
    -0.52
    #!/
    -0.52
     AssemblyCulture
    -0.52
     Hercules
    -0.51
    AndroidJUnit
    -0.51
     arrives
    -0.50
    POSITIVE LOGITS
     movable
    3.03
     moveable
    2.48
    movable
    1.53
     immovable
    0.96
     beweg
    0.62
     JpaRepository
    0.60
     retractable
    0.59
    orianCalendar
    0.58
     removable
    0.55
     noOf
    0.54
    Activations Density 0.001%

    No Known Activations